Upload 2222 files

.gitattributes

@@ -33,3 +33,22 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/markov_autoregression.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/mstl_decomposition.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/recursive_ls.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_bayesian_sarimax.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_chandrasekhar.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_concentrated_scale.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_cycles.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_forecasting.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_sarimax_internet.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_sarimax_pymc3.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_sarimax_stata.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_structural_harvey_jaeger.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/statespace_tvpvar_mcmc_cfa.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/stats_poisson.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/docs/source/_static/images/stl_decomposition.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/examples/notebooks/star_diagram.png filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/statsmodels/datasets/macrodata/src/macrodata.xls/macrodata.xls filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/statsmodels/tsa/statespace/tests/results/frbny_nowcast/Nowcasting/data/US/2016-06-29.xls filter=lfs diff=lfs merge=lfs -text
+statsmodels/source/statsmodels/tsa/statespace/tests/results/frbny_nowcast/Nowcasting/data/US/2016-07-29.xls filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,18 @@
+FROM python:3.10
+
+RUN useradd -m -u 1000 user && python -m pip install --upgrade pip
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+ENV MCP_TRANSPORT=http
+ENV MCP_PORT=7860
+
+EXPOSE 7860
+
+CMD ["python", "statsmodels/mcp_output/start_mcp.py"]

app.py

@@ -0,0 +1,45 @@
+from fastapi import FastAPI
+import os
+import sys
+
+mcp_plugin_path = os.path.join(os.path.dirname(__file__), "statsmodels", "mcp_output", "mcp_plugin")
+sys.path.insert(0, mcp_plugin_path)
+
+app = FastAPI(
+    title="Statsmodels MCP Service",
+    description="Auto-generated MCP service for statsmodels",
+    version="1.0.0"
+)
+
+@app.get("/")
+def root():
+    return {
+        "service": "Statsmodels MCP Service",
+        "version": "1.0.0",
+        "status": "running",
+        "transport": os.environ.get("MCP_TRANSPORT", "http")
+    }
+
+@app.get("/health")
+def health_check():
+    return {"status": "healthy", "service": "statsmodels MCP"}
+
+@app.get("/tools")
+def list_tools():
+    try:
+        from mcp_service import create_app
+        mcp_app = create_app()
+        tools = []
+        for tool_name, tool_func in mcp_app.tools.items():
+            tools.append({
+                "name": tool_name,
+                "description": tool_func.__doc__ or "No description available"
+            })
+        return {"tools": tools}
+    except Exception as e:
+        return {"error": f"Failed to load tools: {str(e)}"}
+
+if __name__ == "__main__":
+    import uvicorn
+    port = int(os.environ.get("PORT", 7860))
+    uvicorn.run(app, host="0.0.0.0", port=port)

port.json

@@ -0,0 +1,5 @@
+{
+  "repo": "statsmodels",
+  "port": 7975,
+  "timestamp": 1773410883
+}

requirements.txt

@@ -0,0 +1,10 @@
+fastmcp
+fastapi
+uvicorn[standard]
+pydantic>=2.0.0
+numpy>=1.22.3,<3  # released March 2022
+scipy>=1.8,!=1.9.2  # released Feb 2022, 1.9.2 blocked due to bug
+pandas>=1.4,!=2.1.0  # released Feb 2022, 2.1.0 blocked due to bug
+patsy>=0.5.6  # released December 2023
+packaging>=21.3  # released Nov 2021
+formulaic>=1.1.0  # released December 2024

run_docker.ps1

@@ -0,0 +1,26 @@
+cd $PSScriptRoot
+$ErrorActionPreference = "Stop"
+$entryName = if ($env:MCP_ENTRY_NAME) { $env:MCP_ENTRY_NAME } else { "statsmodels" }
+$entryUrl  = if ($env:MCP_ENTRY_URL)  { $env:MCP_ENTRY_URL  } else { "http://localhost:7975/mcp" }
+$imageName = if ($env:MCP_IMAGE_NAME) { $env:MCP_IMAGE_NAME } else { "statsmodels-mcp" }
+$mcpDir = Join-Path $env:USERPROFILE ".cursor"
+$mcpPath = Join-Path $mcpDir "mcp.json"
+if (!(Test-Path $mcpDir)) { New-Item -ItemType Directory -Path $mcpDir | Out-Null }
+$config = @{}
+if (Test-Path $mcpPath) {
+  try { $config = Get-Content $mcpPath -Raw | ConvertFrom-Json } catch { $config = @{} }
+}
+$serversOrdered = [ordered]@{}
+if ($config -and ($config.PSObject.Properties.Name -contains "mcpServers") -and $config.mcpServers) {
+  $existing = $config.mcpServers
+  if ($existing -is [pscustomobject]) {
+    foreach ($p in $existing.PSObject.Properties) { if ($p.Name -ne $entryName) { $serversOrdered[$p.Name] = $p.Value } }
+  } elseif ($existing -is [System.Collections.IDictionary]) {
+    foreach ($k in $existing.Keys) { if ($k -ne $entryName) { $serversOrdered[$k] = $existing[$k] } }
+  }
+}
+$serversOrdered[$entryName] = @{ url = $entryUrl }
+$config = @{ mcpServers = $serversOrdered }
+$config | ConvertTo-Json -Depth 10 | Set-Content -Path $mcpPath -Encoding UTF8
+docker build -t $imageName .
+docker run --rm -p 7975:7860 $imageName

run_docker.sh

@@ -0,0 +1,75 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
+mcp_entry_name="${MCP_ENTRY_NAME:-statsmodels}"
+mcp_entry_url="${MCP_ENTRY_URL:-http://localhost:7975/mcp}"
+mcp_dir="${HOME}/.cursor"
+mcp_path="${mcp_dir}/mcp.json"
+mkdir -p "${mcp_dir}"
+if command -v python3 >/dev/null 2>&1; then
+python3 - "${mcp_path}" "${mcp_entry_name}" "${mcp_entry_url}" <<'PY'
+import json, os, sys
+path, name, url = sys.argv[1:4]
+cfg = {"mcpServers": {}}
+if os.path.exists(path):
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            cfg = json.load(f)
+    except Exception:
+        cfg = {"mcpServers": {}}
+if not isinstance(cfg, dict):
+    cfg = {"mcpServers": {}}
+servers = cfg.get("mcpServers")
+if not isinstance(servers, dict):
+    servers = {}
+ordered = {}
+for k, v in servers.items():
+    if k != name:
+        ordered[k] = v
+ordered[name] = {"url": url}
+cfg = {"mcpServers": ordered}
+with open(path, "w", encoding="utf-8") as f:
+    json.dump(cfg, f, indent=2, ensure_ascii=False)
+PY
+elif command -v python >/dev/null 2>&1; then
+python - "${mcp_path}" "${mcp_entry_name}" "${mcp_entry_url}" <<'PY'
+import json, os, sys
+path, name, url = sys.argv[1:4]
+cfg = {"mcpServers": {}}
+if os.path.exists(path):
+    try:
+        with open(path, "r", encoding="utf-8") as f:
+            cfg = json.load(f)
+    except Exception:
+        cfg = {"mcpServers": {}}
+if not isinstance(cfg, dict):
+    cfg = {"mcpServers": {}}
+servers = cfg.get("mcpServers")
+if not isinstance(servers, dict):
+    servers = {}
+ordered = {}
+for k, v in servers.items():
+    if k != name:
+        ordered[k] = v
+ordered[name] = {"url": url}
+cfg = {"mcpServers": ordered}
+with open(path, "w", encoding="utf-8") as f:
+    json.dump(cfg, f, indent=2, ensure_ascii=False)
+PY
+elif command -v jq >/dev/null 2>&1; then
+  name="${mcp_entry_name}"; url="${mcp_entry_url}"
+  if [ -f "${mcp_path}" ]; then
+    tmp="$(mktemp)"
+    jq --arg name "$name" --arg url "$url" '
+      .mcpServers = (.mcpServers // {})
+      | .mcpServers as $s
+      | ($s | with_entries(select(.key != $name))) as $base
+      | .mcpServers = ($base + {($name): {"url": $url}})
+    ' "${mcp_path}" > "${tmp}" && mv "${tmp}" "${mcp_path}"
+  else
+    printf '{ "mcpServers": { "%s": { "url": "%s" } } }
+' "$name" "$url" > "${mcp_path}"
+  fi
+fi
+docker build -t statsmodels-mcp .
+docker run --rm -p 7975:7860 statsmodels-mcp

statsmodels/mcp_output/README_MCP.md

@@ -0,0 +1,150 @@
+# Statsmodels MCP (Model Context Protocol) Service README
+
+## 1) Project Introduction
+
+This MCP (Model Context Protocol) service provides a developer-friendly interface to core `statsmodels` capabilities for statistical modeling, inference, and forecasting.
+
+Main functions:
+- Run classical regression (OLS/WLS/GLS), GLM, and discrete models (Logit/Probit/Poisson)
+- Execute time-series workflows (ARIMA, SARIMAX, decomposition, forecasting)
+- Access statistical tests and diagnostics
+- Load built-in datasets for rapid experimentation
+- Return structured model summaries, parameters, predictions, and diagnostics
+
+Repository: https://github.com/statsmodels/statsmodels
+
+---
+
+## 2) Installation Method
+
+### Requirements
+- Python 3.9+ recommended
+- Core dependencies:
+  - `numpy`
+  - `scipy`
+  - `pandas`
+  - `patsy`
+  - `packaging`
+- Optional (feature-dependent):
+  - `matplotlib` (plots)
+  - `cvxopt` (some optimization paths)
+  - `joblib` (parallel helpers)
+  - `x13as` external binary (for X13 seasonal adjustment workflows)
+
+### Install
+pip install statsmodels numpy scipy pandas patsy packaging
+
+Optional extras:
+pip install matplotlib joblib cvxopt
+
+Environment check:
+python -m statsmodels.tools.print_version
+
+---
+
+## 3) Quick Start
+
+### Basic import path
+Use high-level APIs:
+- `statsmodels.api` (general models/stats)
+- `statsmodels.tsa.api` (time-series)
+- `statsmodels.stats.api` (tests/inference)
+- `statsmodels.formula.api` (formula syntax)
+
+### Typical service flow
+1. Load/receive dataset
+2. Choose model family (`OLS`, `GLM`, `Logit`, `ARIMA`, `SARIMAX`, etc.)
+3. Fit model
+4. Return:
+   - coefficients
+   - confidence intervals
+   - p-values
+   - model diagnostics
+   - predictions/forecasts
+
+### Example call patterns (conceptual)
+- Regression: fit OLS and return summary + residual diagnostics
+- Classification/count: fit Logit/Poisson and return marginal effects
+- Forecasting: fit ARIMA/SARIMAX and return horizon forecasts with intervals
+
+---
+
+## 4) Available Tools and Endpoints List
+
+Recommended MCP (Model Context Protocol) service endpoints:
+
+- `health_check`
+  - Verifies runtime, package availability, and version metadata.
+
+- `get_version_info`
+  - Returns Python/statsmodels/dependency versions (similar to `print_version`).
+
+- `list_datasets`
+  - Lists built-in datasets available from `statsmodels.datasets`.
+
+- `load_dataset`
+  - Loads a selected built-in dataset and returns schema/sample rows.
+
+- `fit_ols`
+  - Fits OLS/WLS/GLS/GLSAR models; returns coefficients and inference statistics.
+
+- `fit_glm`
+  - Fits GLM with configurable family/link; returns fit metrics and inference.
+
+- `fit_discrete_model`
+  - Fits `Logit`, `Probit`, `MNLogit`, `Poisson`, `NegativeBinomial`.
+
+- `fit_arima`
+  - Fits ARIMA models for univariate time series.
+
+- `fit_sarimax`
+  - Fits SARIMAX (seasonality + exogenous regressors + state space engine).
+
+- `forecast`
+  - Produces out-of-sample predictions/forecast intervals for fitted time-series models.
+
+- `run_stat_tests`
+  - Executes common tests (normality, heteroskedasticity, autocorrelation, proportions/power, etc.).
+
+- `model_summary`
+  - Standardized textual/structured summary extraction from fitted results objects.
+
+- `predict`
+  - In-sample or out-of-sample prediction for regression/discrete/GLM models.
+
+---
+
+## 5) Common Issues and Notes
+
+- Binary/scientific stack issues:
+  - Use a clean virtual environment.
+  - Upgrade `pip`, `setuptools`, and `wheel` if installation fails.
+
+- Formula models:
+  - `patsy` is required for formula APIs.
+
+- Time-series advanced features:
+  - Some workflows (e.g., X13) require external binaries not installed by pip.
+
+- Performance:
+  - Large state-space or high-dimensional models can be expensive.
+  - Prefer smaller parameter grids and constrained iteration settings in service contexts.
+
+- Numerical convergence:
+  - Non-convergence can occur for complex models.
+  - Expose optimizer options (maxiter, method, tolerance) in endpoint inputs.
+
+- Reproducibility:
+  - Set random seeds where simulation/resampling is involved.
+  - Return model config + versions in every response payload.
+
+---
+
+## 6) Reference Links / Documentation
+
+- Statsmodels repository: https://github.com/statsmodels/statsmodels
+- Official docs: https://www.statsmodels.org/
+- API reference (entry point): https://www.statsmodels.org/stable/api.html
+- Time series docs: https://www.statsmodels.org/stable/tsa.html
+- Installation notes: https://www.statsmodels.org/stable/install.html
+- Developer docs directory in repo: `docs/`

statsmodels/mcp_output/diff_report.md

@@ -0,0 +1,129 @@
+# Difference Report — `statsmodels`
+
+## 1) Project Overview
+- **Repository:** `statsmodels`
+- **Project Type:** Python library
+- **Feature Scope:** Basic functionality
+- **Report Time:** 2026-03-13 22:07:09
+- **Intrusiveness:** None (non-invasive changes)
+- **Workflow Status:** ✅ Success
+- **Test Status:** ❌ Failed
+
+---
+
+## 2) Change Summary
+| Metric | Value |
+|---|---|
+| New files | 8 |
+| Modified files | 0 |
+| Deleted files | 0 (not reported) |
+| Net impact | Additive-only update |
+
+**Interpretation:**  
+This update introduces new artifacts without altering existing tracked files, indicating low direct regression risk from code modifications—but possible integration or configuration issues due to added assets.
+
+---
+
+## 3) Difference Analysis
+### 3.1 File-Level Difference Pattern
+- **Only new files added (8).**
+- **No existing file edits**, suggesting:
+  - New modules/tests/docs/configs added in parallel
+  - No refactor/rewrite in existing logic paths
+  - Potentially incomplete wiring into package/test system
+
+### 3.2 Functional Impact (Basic Functionality Context)
+Given the “basic functionality” scope:
+- Likely introduces baseline components (e.g., utility modules, starter tests, templates, docs, CI metadata).
+- Since no files were modified, newly added functionality may not yet be invoked by existing workflows unless auto-discovered.
+
+### 3.3 Risk Posture
+- **Code intrusion risk:** Low
+- **Integration risk:** Medium
+- **CI/test reliability risk:** High (because tests failed despite successful workflow execution)
+
+---
+
+## 4) Technical Analysis
+## 4.1 Workflow vs Test Outcome
+A **successful workflow** with **failed tests** typically means:
+1. Build/lint/package steps passed, but runtime assertions failed.
+2. New tests were discovered and failed due to:
+   - Missing fixtures/data
+   - Environment/version assumptions
+   - Numerical tolerance issues (common in stats libraries)
+   - Optional dependency gaps
+3. Test matrix mismatch (e.g., py version, BLAS/LAPACK backend, platform-specific numerics).
+
+## 4.2 Probable Failure Classes for `statsmodels`
+For this project profile, frequent failure vectors include:
+- **Floating-point tolerance drift** (`assert_allclose` thresholds too strict)
+- **Randomized test non-determinism** (seed not fixed)
+- **Pandas/NumPy/SciPy compatibility edge cases**
+- **Import path/package discovery** for newly added files
+- **Doctest/examples failing under strict warning policies**
+
+---
+
+## 5) Recommendations & Improvements
+## 5.1 Immediate Actions (Priority Ordered)
+1. **Collect failing test signatures**
+   - Extract exact test names, stack traces, and environment metadata.
+2. **Classify failures**
+   - Deterministic logic error vs environment/config error.
+3. **Validate discovery/registration**
+   - Ensure new files are correctly included in package/test manifests (`pyproject.toml`, `setup.cfg`, `MANIFEST.in`, pytest config as applicable).
+4. **Stabilize numerics**
+   - Adjust tolerance bands only with statistical justification.
+5. **Re-run targeted subset**
+   - `pytest -k <failing_area> -vv` to shorten feedback loop.
+
+## 5.2 Quality Hardening
+- Add/verify **seed control** in stochastic tests.
+- Enforce **cross-version compatibility gates** for NumPy/Pandas/SciPy.
+- Introduce **smoke tests** for new files to verify importability and minimal execution path.
+- Add **CI artifact upload** for failure logs to accelerate triage.
+
+---
+
+## 6) Deployment / Release Information
+- **Deployment readiness:** ⚠️ Not release-ready (tests failing)
+- **Recommended release gate:** Block merge/release until:
+  - All failing tests are triaged
+  - Root cause fixed or quarantined with justified xfail
+  - Full CI matrix passes (or documented temporary exceptions approved)
+
+- **Change type:** Safe additive structure, but operationally blocked by test failures.
+
+---
+
+## 7) Future Planning
+## 7.1 Short-Term (Next 24–72h)
+- Complete failure triage and patch.
+- Add regression tests tied directly to identified root causes.
+- Re-run full matrix on Linux/macOS/Windows (if supported).
+
+## 7.2 Mid-Term (1–2 sprints)
+- Improve test determinism and numerical robustness policy.
+- Add compatibility CI lanes for upcoming dependency versions.
+- Formalize “new file checklist” (imports, packaging, docs, tests, CI hooks).
+
+## 7.3 Long-Term
+- Establish statistical tolerance governance (per-model/per-solver thresholds).
+- Expand observability of CI failures (structured reporting dashboard).
+- Periodic dependency modernization with pre-merge canary runs.
+
+---
+
+## 8) Suggested Report Addendum (Data Needed)
+To produce a more precise diff report, include:
+- Names/paths of the 8 new files
+- Full failed test log excerpts
+- Python + dependency versions
+- OS/architecture and BLAS backend
+- Whether failures are new vs pre-existing baseline
+
+---
+
+## 9) Executive Conclusion
+This change set is **additive and non-intrusive** at the file-modification level, but **quality gates are not met** due to failed tests. The current state is best treated as an **integration-incomplete update**. Prioritize targeted test triage, package/test registration verification, and numerical stability checks before merge or release.

statsmodels/mcp_output/mcp_plugin/adapter.py

@@ -0,0 +1,281 @@
+import os
+import sys
+import traceback
+import importlib
+from typing import Any, Dict, List, Optional
+
+source_path = os.path.join(
+    os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
+    "source",
+)
+sys.path.insert(0, source_path)
+
+
+class Adapter:
+    """
+    Import-mode adapter for the statsmodels repository.
+
+    This adapter attempts to load modules from the local source tree (source/statsmodels).
+    It exposes utility methods that wrap commonly useful entry points identified in analysis:
+    - statsmodels.api
+    - statsmodels.formula.api
+    - statsmodels.tsa.api
+    - statsmodels.stats.api
+    - statsmodels.graphics.api
+    - statsmodels.tools.print_version (diagnostic module)
+
+    All methods return a unified dictionary format:
+    {
+        "status": "success" | "error" | "fallback",
+        "message": str,
+        ...additional fields...
+    }
+    """
+
+    def __init__(self) -> None:
+        self.mode = "import"
+        self._modules: Dict[str, Any] = {}
+        self._import_errors: Dict[str, str] = {}
+        self._initialize_imports()
+
+    # -------------------------------------------------------------------------
+    # Internal helpers
+    # -------------------------------------------------------------------------
+    def _ok(self, message: str, **kwargs: Any) -> Dict[str, Any]:
+        payload = {"status": "success", "message": message}
+        payload.update(kwargs)
+        return payload
+
+    def _err(self, message: str, **kwargs: Any) -> Dict[str, Any]:
+        payload = {"status": "error", "message": message}
+        payload.update(kwargs)
+        return payload
+
+    def _fallback(self, message: str, **kwargs: Any) -> Dict[str, Any]:
+        payload = {"status": "fallback", "message": message}
+        payload.update(kwargs)
+        return payload
+
+    def _safe_import(self, module_path: str, alias: str) -> None:
+        try:
+            self._modules[alias] = importlib.import_module(module_path)
+        except Exception as exc:
+            self._modules[alias] = None
+            self._import_errors[alias] = f"{type(exc).__name__}: {exc}"
+
+    def _initialize_imports(self) -> None:
+        self._safe_import("statsmodels", "statsmodels_root")
+        self._safe_import("statsmodels.api", "sm_api")
+        self._safe_import("statsmodels.formula.api", "smf_api")
+        self._safe_import("statsmodels.tsa.api", "tsa_api")
+        self._safe_import("statsmodels.stats.api", "stats_api")
+        self._safe_import("statsmodels.graphics.api", "graphics_api")
+        self._safe_import("statsmodels.tools.print_version", "print_version_mod")
+
+    def _require_module(self, alias: str, guidance: Optional[str] = None) -> Dict[str, Any]:
+        mod = self._modules.get(alias)
+        if mod is not None:
+            return self._ok("Module is available.", module=alias)
+        msg = self._import_errors.get(alias, "Module import failed for unknown reasons.")
+        help_msg = guidance or "Verify local source path and required dependencies are installed."
+        return self._fallback(
+            f"Module '{alias}' is unavailable. {msg}",
+            guidance=help_msg,
+            import_error=msg,
+            module=alias,
+        )
+
+    # -------------------------------------------------------------------------
+    # Health / diagnostics
+    # -------------------------------------------------------------------------
+    def health_check(self) -> Dict[str, Any]:
+        available = [k for k, v in self._modules.items() if v is not None]
+        unavailable = {k: self._import_errors.get(k, "Unknown error") for k, v in self._modules.items() if v is None}
+        return self._ok(
+            "Adapter initialized.",
+            mode=self.mode,
+            source_path=source_path,
+            available_modules=available,
+            unavailable_modules=unavailable,
+        )
+
+    def get_version(self) -> Dict[str, Any]:
+        mod = self._modules.get("statsmodels_root")
+        if mod is None:
+            return self._require_module("statsmodels_root", "Ensure source/statsmodels is present and importable.")
+        version = getattr(mod, "__version__", None)
+        return self._ok("Version retrieved.", version=version)
+
+    def call_print_version_module(self) -> Dict[str, Any]:
+        check = self._require_module("print_version_mod", "Try importing statsmodels.tools.print_version directly.")
+        if check["status"] != "success":
+            return check
+        mod = self._modules["print_version_mod"]
+        attrs = [a for a in dir(mod) if not a.startswith("_")]
+        return self._ok(
+            "Diagnostic module loaded.",
+            module="statsmodels.tools.print_version",
+            public_attributes=attrs,
+            note="This module is intended for environment/version diagnostics.",
+        )
+
+    # -------------------------------------------------------------------------
+    # API module accessors
+    # -------------------------------------------------------------------------
+    def instance_statsmodels_api(self) -> Dict[str, Any]:
+        return self._require_module("sm_api", "Install required dependencies: numpy, scipy, pandas, patsy, packaging.")
+
+    def instance_formula_api(self) -> Dict[str, Any]:
+        return self._require_module("smf_api", "Ensure patsy is installed for formula support.")
+
+    def instance_tsa_api(self) -> Dict[str, Any]:
+        return self._require_module("tsa_api", "Ensure time-series dependencies are available (numpy/scipy/pandas).")
+
+    def instance_stats_api(self) -> Dict[str, Any]:
+        return self._require_module("stats_api", "Ensure core scientific dependencies are available.")
+
+    def instance_graphics_api(self) -> Dict[str, Any]:
+        return self._require_module("graphics_api", "Install matplotlib for plotting-related features.")
+
+    # -------------------------------------------------------------------------
+    # Dynamic class/function execution utilities
+    # -------------------------------------------------------------------------
+    def create_instance(self, module_alias: str, class_name: str, *args: Any, **kwargs: Any) -> Dict[str, Any]:
+        """
+        Create an instance of a class from an imported module alias.
+
+        Parameters:
+            module_alias: One of the imported aliases (e.g., 'sm_api', 'tsa_api').
+            class_name: Exact class name to instantiate.
+            *args, **kwargs: Constructor parameters.
+
+        Returns:
+            Unified status dictionary with created instance (if successful).
+        """
+        check = self._require_module(module_alias)
+        if check["status"] != "success":
+            return check
+        mod = self._modules[module_alias]
+        try:
+            cls = getattr(mod, class_name)
+            instance = cls(*args, **kwargs)
+            return self._ok(
+                "Class instance created.",
+                module_alias=module_alias,
+                class_name=class_name,
+                instance=instance,
+            )
+        except AttributeError:
+            return self._err(
+                f"Class '{class_name}' was not found in module alias '{module_alias}'.",
+                guidance="Verify class name and module alias.",
+            )
+        except Exception as exc:
+            return self._err(
+                f"Failed to instantiate class '{class_name}'.",
+                error=f"{type(exc).__name__}: {exc}",
+                traceback=traceback.format_exc(),
+            )
+
+    def call_function(self, module_alias: str, function_name: str, *args: Any, **kwargs: Any) -> Dict[str, Any]:
+        """
+        Call a function from an imported module alias.
+
+        Parameters:
+            module_alias: One of the imported aliases (e.g., 'sm_api', 'smf_api', 'tsa_api').
+            function_name: Function name to call.
+            *args, **kwargs: Function parameters.
+
+        Returns:
+            Unified status dictionary with function result.
+        """
+        check = self._require_module(module_alias)
+        if check["status"] != "success":
+            return check
+        mod = self._modules[module_alias]
+        try:
+            fn = getattr(mod, function_name)
+            result = fn(*args, **kwargs)
+            return self._ok(
+                "Function executed successfully.",
+                module_alias=module_alias,
+                function_name=function_name,
+                result=result,
+            )
+        except AttributeError:
+            return self._err(
+                f"Function '{function_name}' was not found in module alias '{module_alias}'.",
+                guidance="Verify function name and module alias.",
+            )
+        except Exception as exc:
+            return self._err(
+                f"Function '{function_name}' execution failed.",
+                error=f"{type(exc).__name__}: {exc}",
+                traceback=traceback.format_exc(),
+            )
+
+    # -------------------------------------------------------------------------
+    # Convenience wrappers for common statsmodels usage
+    # -------------------------------------------------------------------------
+    def list_public_members(self, module_alias: str) -> Dict[str, Any]:
+        check = self._require_module(module_alias)
+        if check["status"] != "success":
+            return check
+        mod = self._modules[module_alias]
+        public = [a for a in dir(mod) if not a.startswith("_")]
+        return self._ok("Public members listed.", module_alias=module_alias, members=public)
+
+    def run_module_function(self, full_module_path: str, function_name: str, *args: Any, **kwargs: Any) -> Dict[str, Any]:
+        """
+        Import any module by full path and execute one function.
+
+        Parameters:
+            full_module_path: e.g., 'statsmodels.tools.print_version'
+            function_name: function to call inside module
+            *args, **kwargs: function arguments
+
+        Returns:
+            Unified status dictionary.
+        """
+        try:
+            mod = importlib.import_module(full_module_path)
+            fn = getattr(mod, function_name)
+            result = fn(*args, **kwargs)
+            return self._ok(
+                "Module function executed successfully.",
+                module=full_module_path,
+                function=function_name,
+                result=result,
+            )
+        except ModuleNotFoundError:
+            return self._fallback(
+                f"Module '{full_module_path}' could not be imported.",
+                guidance="Check source path and ensure repository source files are available.",
+            )
+        except AttributeError:
+            return self._err(
+                f"Function '{function_name}' was not found in module '{full_module_path}'.",
+                guidance="Verify function name and module path.",
+            )
+        except Exception as exc:
+            return self._err(
+                f"Execution failed for '{full_module_path}.{function_name}'.",
+                error=f"{type(exc).__name__}: {exc}",
+                traceback=traceback.format_exc(),
+            )
+
+    def supported_modules(self) -> Dict[str, Any]:
+        return self._ok(
+            "Supported module aliases returned.",
+            aliases={
+                "statsmodels_root": "statsmodels",
+                "sm_api": "statsmodels.api",
+                "smf_api": "statsmodels.formula.api",
+                "tsa_api": "statsmodels.tsa.api",
+                "stats_api": "statsmodels.stats.api",
+                "graphics_api": "statsmodels.graphics.api",
+                "print_version_mod": "statsmodels.tools.print_version",
+            },
+            required_dependencies=["numpy", "scipy", "pandas", "patsy", "packaging"],
+            optional_dependencies=["matplotlib", "cvxopt", "joblib", "pytest", "x13as external binary"],
+        )

statsmodels/mcp_output/mcp_plugin/main.py

@@ -0,0 +1,13 @@
+"""
+MCP Service Auto-Wrapper - Auto-generated
+"""
+from mcp_service import create_app
+
+def main():
+    """Main entry point"""
+    app = create_app()
+    return app
+
+if __name__ == "__main__":
+    app = main()
+    app.run()

statsmodels/mcp_output/mcp_plugin/mcp_service.py

@@ -0,0 +1,308 @@
+import os
+import sys
+from typing import Any, Dict, List, Optional
+
+source_path = os.path.join(
+    os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))),
+    "source",
+)
+if source_path not in sys.path:
+    sys.path.insert(0, source_path)
+
+from fastmcp import FastMCP
+import numpy as np
+import pandas as pd
+import statsmodels.api as sm
+from statsmodels.tsa.api import ARIMA
+from statsmodels.stats.diagnostic import acorr_ljungbox
+from statsmodels.stats.stattools import jarque_bera
+
+mcp = FastMCP("statsmodels_service")
+
+
+def _ok(result: Any) -> Dict[str, Any]:
+    return {"success": True, "result": result, "error": None}
+
+
+def _err(exc: Exception) -> Dict[str, Any]:
+    return {"success": False, "result": None, "error": str(exc)}
+
+
+@mcp.tool(name="ols_fit", description="Fit an OLS regression model and return summary metrics.")
+def ols_fit(
+    y: List[float],
+    X: List[List[float]],
+    add_constant: bool = True,
+) -> Dict[str, Any]:
+    """
+    Fit an Ordinary Least Squares (OLS) model.
+
+    Parameters:
+    - y: Dependent variable values.
+    - X: 2D feature matrix where each inner list is one observation.
+    - add_constant: If True, prepends an intercept column.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result contains coefficients,
+      p-values, R-squared, adjusted R-squared, AIC, BIC, and observation count.
+    """
+    try:
+        y_arr = np.asarray(y, dtype=float)
+        X_arr = np.asarray(X, dtype=float)
+        if add_constant:
+            X_arr = sm.add_constant(X_arr, has_constant="add")
+        model = sm.OLS(y_arr, X_arr).fit()
+        return _ok(
+            {
+                "params": model.params.tolist(),
+                "pvalues": model.pvalues.tolist(),
+                "rsquared": float(model.rsquared),
+                "rsquared_adj": float(model.rsquared_adj),
+                "aic": float(model.aic),
+                "bic": float(model.bic),
+                "nobs": int(model.nobs),
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+@mcp.tool(name="glm_fit", description="Fit a GLM model for common families (gaussian, binomial, poisson).")
+def glm_fit(
+    y: List[float],
+    X: List[List[float]],
+    family: str = "gaussian",
+    add_constant: bool = True,
+) -> Dict[str, Any]:
+    """
+    Fit a Generalized Linear Model (GLM).
+
+    Parameters:
+    - y: Response values.
+    - X: 2D feature matrix.
+    - family: One of 'gaussian', 'binomial', 'poisson'.
+    - add_constant: If True, prepends an intercept column.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result contains coefficients,
+      standard errors, p-values, deviance, and observation count.
+    """
+    try:
+        fam = family.lower().strip()
+        if fam == "gaussian":
+            fam_obj = sm.families.Gaussian()
+        elif fam == "binomial":
+            fam_obj = sm.families.Binomial()
+        elif fam == "poisson":
+            fam_obj = sm.families.Poisson()
+        else:
+            raise ValueError("family must be one of: gaussian, binomial, poisson")
+
+        y_arr = np.asarray(y, dtype=float)
+        X_arr = np.asarray(X, dtype=float)
+        if add_constant:
+            X_arr = sm.add_constant(X_arr, has_constant="add")
+        model = sm.GLM(y_arr, X_arr, family=fam_obj).fit()
+        return _ok(
+            {
+                "params": model.params.tolist(),
+                "bse": model.bse.tolist(),
+                "pvalues": model.pvalues.tolist(),
+                "deviance": float(model.deviance),
+                "nobs": int(model.nobs),
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+@mcp.tool(name="logit_fit", description="Fit a logistic regression model.")
+def logit_fit(
+    y: List[int],
+    X: List[List[float]],
+    add_constant: bool = True,
+    maxiter: int = 100,
+) -> Dict[str, Any]:
+    """
+    Fit a Logit (binary logistic regression) model.
+
+    Parameters:
+    - y: Binary response values (0/1).
+    - X: 2D feature matrix.
+    - add_constant: If True, prepends an intercept column.
+    - maxiter: Maximum optimizer iterations.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result contains coefficients,
+      p-values, pseudo R-squared, log-likelihood, and convergence flag.
+    """
+    try:
+        y_arr = np.asarray(y, dtype=float)
+        X_arr = np.asarray(X, dtype=float)
+        if add_constant:
+            X_arr = sm.add_constant(X_arr, has_constant="add")
+        model = sm.Logit(y_arr, X_arr).fit(disp=0, maxiter=maxiter)
+        return _ok(
+            {
+                "params": model.params.tolist(),
+                "pvalues": model.pvalues.tolist(),
+                "prsquared": float(model.prsquared),
+                "llf": float(model.llf),
+                "converged": bool(model.mle_retvals.get("converged", False)),
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+@mcp.tool(name="arima_fit_forecast", description="Fit ARIMA model and forecast future values.")
+def arima_fit_forecast(
+    y: List[float],
+    p: int = 1,
+    d: int = 0,
+    q: int = 0,
+    steps: int = 5,
+) -> Dict[str, Any]:
+    """
+    Fit an ARIMA model and produce forecasts.
+
+    Parameters:
+    - y: Univariate time series.
+    - p: AR order.
+    - d: Differencing order.
+    - q: MA order.
+    - steps: Number of forecast steps.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result includes fitted params,
+      AIC/BIC, and forecast values.
+    """
+    try:
+        y_arr = np.asarray(y, dtype=float)
+        model = ARIMA(y_arr, order=(p, d, q)).fit()
+        forecast = model.forecast(steps=steps)
+        return _ok(
+            {
+                "params": model.params.tolist(),
+                "aic": float(model.aic),
+                "bic": float(model.bic),
+                "forecast": np.asarray(forecast).tolist(),
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+@mcp.tool(name="seasonal_decompose", description="Perform additive or multiplicative seasonal decomposition.")
+def seasonal_decompose(
+    y: List[float],
+    period: int,
+    model: str = "additive",
+) -> Dict[str, Any]:
+    """
+    Decompose a time series into trend/seasonal/residual components.
+
+    Parameters:
+    - y: Univariate time series.
+    - period: Seasonal period length.
+    - model: 'additive' or 'multiplicative'.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result contains trend,
+      seasonal, and residual arrays (NaNs converted to None).
+    """
+    try:
+        from statsmodels.tsa.seasonal import seasonal_decompose as sm_seasonal_decompose
+
+        y_arr = pd.Series(np.asarray(y, dtype=float))
+        dec = sm_seasonal_decompose(y_arr, model=model, period=period, extrapolate_trend="freq")
+
+        def clean(values: pd.Series) -> List[Optional[float]]:
+            out: List[Optional[float]] = []
+            for v in values.to_numpy():
+                out.append(None if pd.isna(v) else float(v))
+            return out
+
+        return _ok(
+            {
+                "trend": clean(dec.trend),
+                "seasonal": clean(dec.seasonal),
+                "resid": clean(dec.resid),
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+@mcp.tool(name="diagnostic_tests", description="Run Jarque-Bera and Ljung-Box diagnostic tests.")
+def diagnostic_tests(
+    residuals: List[float],
+    lags: int = 10,
+) -> Dict[str, Any]:
+    """
+    Run common residual diagnostics.
+
+    Parameters:
+    - residuals: Residual series from a fitted model.
+    - lags: Number of lags for Ljung-Box test.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result contains Jarque-Bera
+      statistic/p-value/skew/kurtosis and Ljung-Box test table.
+    """
+    try:
+        resid = np.asarray(residuals, dtype=float)
+        jb_stat, jb_pvalue, skew, kurt = jarque_bera(resid)
+        lb = acorr_ljungbox(resid, lags=[lags], return_df=True)
+        return _ok(
+            {
+                "jarque_bera": {
+                    "statistic": float(jb_stat),
+                    "pvalue": float(jb_pvalue),
+                    "skew": float(skew),
+                    "kurtosis": float(kurt),
+                },
+                "ljung_box": lb.reset_index().to_dict(orient="records"),
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+@mcp.tool(name="load_dataset", description="Load a built-in statsmodels dataset as records.")
+def load_dataset(
+    dataset_name: str,
+    max_rows: int = 20,
+) -> Dict[str, Any]:
+    """
+    Load a built-in dataset from statsmodels.datasets.
+
+    Parameters:
+    - dataset_name: Dataset module name (e.g., 'longley', 'macrodata', 'sunspots').
+    - max_rows: Maximum number of rows to return.
+
+    Returns:
+    - Dictionary with success/result/error fields. Result contains dataset
+      metadata and sample records.
+    """
+    try:
+        import importlib
+
+        ds_module = importlib.import_module(f"statsmodels.datasets.{dataset_name}.data")
+        loaded = ds_module.load_pandas()
+        df = loaded.data.copy()
+        sample = df.head(max_rows).to_dict(orient="records")
+        return _ok(
+            {
+                "dataset_name": dataset_name,
+                "columns": list(df.columns),
+                "nrows": int(df.shape[0]),
+                "sample": sample,
+            }
+        )
+    except Exception as exc:
+        return _err(exc)
+
+
+def create_app() -> FastMCP:
+    return mcp

statsmodels/mcp_output/requirements.txt

@@ -0,0 +1,10 @@
+fastmcp
+fastapi
+uvicorn[standard]
+pydantic>=2.0.0
+numpy>=1.22.3,<3  # released March 2022
+scipy>=1.8,!=1.9.2  # released Feb 2022, 1.9.2 blocked due to bug
+pandas>=1.4,!=2.1.0  # released Feb 2022, 2.1.0 blocked due to bug
+patsy>=0.5.6  # released December 2023
+packaging>=21.3  # released Nov 2021
+formulaic>=1.1.0  # released December 2024

statsmodels/mcp_output/start_mcp.py

@@ -0,0 +1,30 @@
+
+"""
+MCP Service Startup Entry
+"""
+import sys
+import os
+
+project_root = os.path.dirname(os.path.abspath(__file__))
+mcp_plugin_dir = os.path.join(project_root, "mcp_plugin")
+if mcp_plugin_dir not in sys.path:
+    sys.path.insert(0, mcp_plugin_dir)
+
+from mcp_service import create_app
+
+def main():
+    """Start FastMCP service"""
+    app = create_app()
+    # Use environment variable to configure port, default 8000
+    port = int(os.environ.get("MCP_PORT", "8000"))
+    
+    # Choose transport mode based on environment variable
+    transport = os.environ.get("MCP_TRANSPORT", "stdio")
+    if transport == "http":
+        app.run(transport="http", host="0.0.0.0", port=port)
+    else:
+        # Default to STDIO mode
+        app.run()
+
+if __name__ == "__main__":
+    main()

statsmodels/mcp_output/workflow_summary.json

@@ -0,0 +1,244 @@
+{
+  "repository": {
+    "name": "statsmodels",
+    "url": "https://github.com/statsmodels/statsmodels",
+    "local_path": "/Users/ghh/Documents/Code/Code2MCP-private/workspace/statsmodels",
+    "description": "Python library",
+    "features": "Basic functionality",
+    "tech_stack": "Python",
+    "stars": 0,
+    "forks": 0,
+    "language": "Python",
+    "last_updated": "",
+    "complexity": "medium",
+    "intrusiveness_risk": "low"
+  },
+  "execution": {
+    "start_time": 1773410486.756045,
+    "end_time": 1773410695.732192,
+    "duration": 208.97614693641663,
+    "status": "success",
+    "workflow_status": "success",
+    "nodes_executed": [
+      "download",
+      "analysis",
+      "env",
+      "generate",
+      "run",
+      "review",
+      "finalize"
+    ],
+    "total_files_processed": 30,
+    "environment_type": "unknown",
+    "llm_calls": 0,
+    "deepwiki_calls": 0
+  },
+  "tests": {
+    "original_project": {
+      "passed": false,
+      "details": {},
+      "test_coverage": "100%",
+      "execution_time": 0,
+      "test_files": []
+    },
+    "mcp_plugin": {
+      "passed": true,
+      "details": {},
+      "service_health": "healthy",
+      "startup_time": 0,
+      "transport_mode": "stdio",
+      "fastmcp_version": "unknown",
+      "mcp_version": "unknown"
+    }
+  },
+  "analysis": {
+    "structure": {
+      "packages": [
+        "deployment.statsmodels.source",
+        "mcp_output.mcp_plugin",
+        "source.statsmodels",
+        "source.statsmodels._build",
+        "source.statsmodels.base",
+        "source.statsmodels.compat",
+        "source.statsmodels.datasets",
+        "source.statsmodels.discrete",
+        "source.statsmodels.distributions",
+        "source.statsmodels.duration",
+        "source.statsmodels.emplike",
+        "source.statsmodels.formula",
+        "source.statsmodels.gam",
+        "source.statsmodels.genmod",
+        "source.statsmodels.graphics",
+        "source.statsmodels.imputation",
+        "source.statsmodels.includes",
+        "source.statsmodels.iolib",
+        "source.statsmodels.miscmodels",
+        "source.statsmodels.multivariate",
+        "source.statsmodels.nonparametric",
+        "source.statsmodels.othermod",
+        "source.statsmodels.regression",
+        "source.statsmodels.robust",
+        "source.statsmodels.sandbox",
+        "source.statsmodels.stats",
+        "source.statsmodels.tests",
+        "source.statsmodels.tools",
+        "source.statsmodels.treatment",
+        "source.statsmodels.tsa"
+      ]
+    },
+    "dependencies": {
+      "has_environment_yml": false,
+      "has_requirements_txt": true,
+      "pyproject": true,
+      "setup_cfg": false,
+      "setup_py": false
+    },
+    "entry_points": {
+      "imports": [],
+      "cli": [],
+      "modules": []
+    },
+    "risk_assessment": {
+      "import_feasibility": 0.95,
+      "intrusiveness_risk": "low",
+      "complexity": "medium"
+    },
+    "deepwiki_analysis": {
+      "repo_url": "https://github.com/statsmodels/statsmodels",
+      "repo_name": "statsmodels",
+      "error": "DeepWiki analysis failed",
+      "model": "gpt-5.3-codex",
+      "source": "llm_direct_analysis",
+      "success": false
+    },
+    "code_complexity": {
+      "cyclomatic_complexity": "medium",
+      "cognitive_complexity": "medium",
+      "maintainability_index": 75
+    },
+    "security_analysis": {
+      "vulnerabilities_found": 0,
+      "security_score": 85,
+      "recommendations": []
+    }
+  },
+  "plugin_generation": {
+    "files_created": [
+      "mcp_output/start_mcp.py",
+      "mcp_output/mcp_plugin/__init__.py",
+      "mcp_output/mcp_plugin/mcp_service.py",
+      "mcp_output/mcp_plugin/adapter.py",
+      "mcp_output/mcp_plugin/main.py",
+      "mcp_output/requirements.txt",
+      "mcp_output/README_MCP.md"
+    ],
+    "main_entry": "start_mcp.py",
+    "requirements": [
+      "fastmcp>=0.1.0",
+      "pydantic>=2.0.0"
+    ],
+    "readme_path": "/Users/ghh/Documents/Code/Code2MCP-private/workspace/statsmodels/mcp_output/README_MCP.md",
+    "adapter_mode": "import",
+    "total_lines_of_code": 0,
+    "generated_files_size": 0,
+    "tool_endpoints": 0,
+    "supported_features": [
+      "Basic functionality"
+    ],
+    "generated_tools": [
+      "Basic tools",
+      "Health check tools",
+      "Version info tools"
+    ]
+  },
+  "code_review": {},
+  "errors": [],
+  "warnings": [],
+  "recommendations": [
+    "add a minimal smoke test suite for MCP endpoints (fit/predict roundtrips for OLS/GLM/ARIMA/SARIMAX) since test status is empty",
+    "add input/output pydantic schemas per endpoint (typed params",
+    "defaults",
+    "validation errors) to reduce runtime misuse",
+    "pin and sync dependency ranges between root `pyproject.toml` and `mcp_output/requirements.txt` (including compatible numpy/scipy/pandas windows)",
+    "implement robust exception mapping in `mcp_service.py` (user error vs numerical convergence vs internal error) with consistent error payloads",
+    "add timeout and resource guards for heavy models (especially SARIMAX/ARIMA) to prevent long-running MCP calls",
+    "include deterministic tiny built-in datasets/fixtures for endpoint tests to avoid flaky external dependencies",
+    "add CI workflow specifically for `mcp_output` (lint",
+    "type-check",
+    "unit tests",
+    "import test against released statsmodels)",
+    "expand endpoint coverage beyond class constructors to practical operations (`fit`",
+    "`summary`",
+    "`predict`",
+    "`get_prediction`) as explicit tools",
+    "create version compatibility checks at server startup (report statsmodels/numpy/scipy versions and warn on unsupported combos)",
+    "add structured logging and request IDs in adapter/service layers for debuggability",
+    "document endpoint parameter conventions and common gotchas in `README_MCP.md` with copy-paste examples",
+    "introduce mypy/ruff on plugin code to catch interface drift early",
+    "add contract tests that compare MCP outputs to direct statsmodels calls for the same seed/data",
+    "implement graceful degradation for optional features (e.g.",
+    "x13-dependent functionality) with clear capability flags",
+    "add basic performance benchmarks for key endpoints (latency/memory on small/medium datasets) and track regressions in CI"
+  ],
+  "performance_metrics": {
+    "memory_usage_mb": 0,
+    "cpu_usage_percent": 0,
+    "response_time_ms": 0,
+    "throughput_requests_per_second": 0
+  },
+  "deployment_info": {
+    "supported_platforms": [
+      "Linux",
+      "Windows",
+      "macOS"
+    ],
+    "python_versions": [
+      "3.8",
+      "3.9",
+      "3.10",
+      "3.11",
+      "3.12"
+    ],
+    "deployment_methods": [
+      "Docker",
+      "pip",
+      "conda"
+    ],
+    "monitoring_support": true,
+    "logging_configuration": "structured"
+  },
+  "execution_analysis": {
+    "success_factors": [
+      "End-to-end workflow status is success, and all planned nodes executed (download, analysis, env, generate, run, review, finalize).",
+      "Import-based adapter strategy was feasible for statsmodels (import feasibility ~0.95), reducing integration friction.",
+      "Generated MCP service started healthy over stdio transport, indicating baseline runtime viability.",
+      "Repository analysis correctly identified core modules and generated endpoint set aligned with common statsmodels classes (OLS/GLM/Logit/ARIMA/SARIMAX)."
+    ],
+    "failure_reasons": [
+      "No hard workflow failure occurred.",
+      "Validation depth is insufficient: original project tests show passed=false with empty details, and MCP tests are effectively absent (no concrete endpoint test evidence).",
+      "Observability gaps (resource metrics all zero/empty, generated LOC/size recorded as zero) indicate instrumentation/reporting defects.",
+      "DeepWiki analysis failed, reducing external semantic enrichment for generation confidence."
+    ],
+    "overall_assessment": "good",
+    "node_performance": {
+      "download_time": "Completed successfully; likely moderate due to large repo (1441 files) imported via zip fallback.",
+      "analysis_time": "Completed successfully with broad structural/dependency mapping; likely the dominant step given repository size and package breadth.",
+      "generation_time": "Completed successfully; plugin scaffold and core service files created, but metadata quality is weak (0 LOC/size/tool endpoint counts).",
+      "test_time": "Service health check passed, but functional test coverage is effectively missing; quality signal is low despite green status."
+    },
+    "resource_usage": {
+      "memory_efficiency": "Not assessable from provided metrics (reported as 0). Add real memory profiling during analysis/generation/run.",
+      "cpu_efficiency": "Not assessable from provided metrics (reported as 0). Capture per-node CPU utilization and hotspots.",
+      "disk_usage": "Repo is large; generated artifact footprint appears underreported (size=0). Add artifact size accounting and cache usage stats."
+    }
+  },
+  "technical_quality": {
+    "code_quality_score": 72,
+    "architecture_score": 78,
+    "performance_score": 60,
+    "maintainability_score": 70,
+    "security_score": 85,
+    "scalability_score": 68
+  }
+}

statsmodels/source/.codacy.yml

@@ -0,0 +1,7 @@
+---
+engines:
+ pylint:
+   enabled: true
+   python_version: 3
+exclude_paths:
+  - '**/_version.py'

statsmodels/source/.flake8

@@ -0,0 +1,22 @@
+[flake8]
+exclude = .git,build,docs,archive
+max-line-length = 88
+extend-select =
+    B904,
+    # B905, # Enable when Python 3.10 is the minimum
+
+extend-ignore =
+    # Required to allow black formatting
+    E203,
+    # E203: Whitespace before ':' (Needed for black)
+    E501,
+    # E501: Line too long (### > 88 characters) (Needed for black)
+    E701,
+    # E701: Multiple statements on one line (colon) (Needed for black)
+
+per-file-ignores =
+    statsmodels/examples/tests/test_notebooks.py: F401
+    statsmodels/discrete/tests/results/results_predict.py: E131, E251
+    statsmodels/discrete/tests/results/results_truncated_st.py: E131, E251
+    statsmodels/treatment/tests/results/results_teffects.py: E124, E128, E131
+

statsmodels/source/.mailmap

@@ -0,0 +1,97 @@
+Alexander W Blocker <ablocker@gmail.com>  Alexander W Blocker <ablocker@gmail.com> 
+Alex Griffing <argriffi@ncsu.edu> alex <argriffi@ncsu.edu>
+Alexis Roche <alexis.roche@gmail.com>  Alexis Roche <alexis.roche@gmail.com> 
+Ana Martinez Pardo <anamartinezpardo@gmail.com>  Ana Martinez Pardo <anamartinezpardo@gmail.com> 
+Ana Martinez Pardo <anamartinezpardo@gmail.com>  Ana Martinez Pardo <anamartinezpardo@gmailcom> 
+anov <novikova.go.zoom@gmail.com>  anov <novikova.go.zoom@gmail.com> 
+avishaylivne <avishay.livne@gmail.com>  avishaylivne <avishay.livne@gmail.com> 
+Bart Baker <bartbkr@gmail.com>  Bart Baker <bartbkr@gmail.com> 
+Bart Baker <bartbkr@gmail.com>  bartbkr <bartbkr@gmail.com> 
+Bart Baker <bartbkr@gmail.com>  bartbkr@gmail.com <bart@bart-Inspiron-1525.(none)> 
+Ben Duffield <bduffield@palantir.com> benduffield <bduffield@palantir.com>
+Benjamin Thyreau <benjamin@neron>  benjamin.thyreau <> 
+brian.hawthorne <>  brian.hawthorne <> 
+Bruno Rodrigues <rodrigues.bruno@aquitania.org>  Bruno Rodrigues <rodrigues.bruno@aquitania.org> 
+Carl Vogel <carljv@gmail.com>  Carl Vogel <carljv@gmail.com> 
+Chad Fulton <chad@chadfulton.com>  Chad Fulton <chad@chadfulton.com> 
+Chris Jordan-Squire <cjordan1@uw.edu>  Chris Jordan-Squire <cjordan1@uw.edu> 
+Christian Prinoth <christian@prinoth.name>  Christian Prinoth <christian@prinoth.name> 
+Christopher Burns  cburns <> 
+Christopher Burns <cburns@localhost.localdomain>  Chris <cburns@localhost.localdomain> 
+Christopher Burns <cburns@berkeley.edu>  Christopher Burns <cburns@berkeley.edu> 
+Cindee Madison <cindee@berkeley.edu>  Cindee Madison <cindeem@8d8.local> 
+Daniel B. Smith <neuromathdan@gmail.com>  Daniel B. Smith <neuromathdan@gmail.com> 
+davclark <>  davclark <> 
+dengemann <denis.engemann@gmail.com>  dengemann <denis.engemann@gmail.com> 
+Dieter Vandenbussche <dvandenbussche@axioma.com>  Dieter Vandenbussche <dvandenbussche@axioma.com> 
+Dougal Sutherland <dougal@gmail.com>  Dougal Sutherland <dougal@gmail.com> 
+Enrico Giampieri <enrico.giampieri@unibo.it>  Enrico Giampieri <enrico.giampieri@unibo.it> 
+Eric Chiang <eric.chiang.m@gmail.com> ericchiang <eric.chiang.m@gmail.com>
+evelynmitchell <efm-github@linsomniac.com>  evelynmitchell <efm-github@linsomniac.com> 
+Evgeni Burovski <evgeni@burovski.me> Zhenya <evgeni@burovski.me>
+Fernando Perez <Fernando.Perez@berkeley.edu>  fdo.perez <> 
+Fernando Perez <Fernando.Perez@berkeley.edu>  Fernando Perez <Fernando.Perez@berkeley.edu> 
+Gael Varoquaux <gael.varoquaux@normalesup.org>  Gael Varoquaux <gael.varoquaux@normalesup.org> 
+George Panterov <econgpanterov@gmail.com>  George Panterov <econgpanterov@gmail.com> 
+Grayson <graysonbadgley@gmail.com>  Grayson <graysonbadgley@gmail.com> 
+Jan Schulz <jasc@gmx.net>  Jan Schulz <jasc@gmx.net> 
+Jarrod Millman <jarrod.millman@gmail.com>  jarrod.millman <> 
+Jarrod Millman <jarrod.millman@gmail.com>  Jarrod Millman <millman@berkeley.edu> 
+Jeff Reback <jeff@reback.net> jreback <jeff@reback.net>
+Jonathan Taylor <jtaylo@miller.stanford.edu>  jonathan.taylor <> 
+Jonathan Taylor <jtaylo@miller.stanford.edu>  Jonathan Taylor <jonathan.taylor@stanford.edu> 
+Jonathan Taylor <jtaylo@miller.stanford.edu>  Jonathan Taylor <jtaylo@dell-desktop> 
+Jonathan Taylor <jtaylo@miller.stanford.edu>  Jonathan Taylor <jtaylo@grf> 
+Jonathan Taylor <jtaylo@miller.stanford.edu>  Jonathan Taylor <jtaylo@kff> 
+Jonathan Taylor <jtaylo@miller.stanford.edu>  jtaylo <jtaylo@ubuntu.dms.umontreal.ca> 
+Josef Perktold <josef.pktd@gmail.com>  Josef Perktold <josef.pktd@gmail.com> 
+Justin Grana <jg3705a@student.american.edu>  Justin Grana <jg3705a@student.american.edu> 
+langmore <ianlangmore@gmail.com>  langmore <ianlangmore@gmail.com> 
+Matthew Brett <matthew.brett@gmail.com>   matthew.brett <> 
+Matthew Brett <matthew.brett@gmail.com>   Matthew Brett <> 
+Matthew Brett <matthew.brett@gmail.com>  Matthew Brett <matthew.brett@gmail.com> 
+Matthew Brett <matthew.brett@gmail.com>   Matthew Brett <mb312@millroad> 
+Matthieu Brucher <matthieu.brucher@gmail.com>  Matthieu Brucher <matthieu.brucher@gmail.com> 
+michael.castelle <>  michael.castelle <> 
+Mike Crowe <m.j.a.crowe@gmail.com>  Mike Crowe <m.j.a.crowe@gmail.com> 
+Mike Crowe <m.j.a.crowe@gmail.com>  Mike Crowe <m.j.a.crowe@googlemail.com> 
+Mike Crowe <m.j.a.crowe@gmail.com>  Mike <m.j.a.crowe@googlemail.com> 
+Nathaniel J. Smith <njs@pobox.com>  Nathaniel J. Smith <njs@pobox.com> 
+otterb <itoi@live.com>  otterb <itoi@live.com> 
+Padarn Wilson <padarn@wilsonp.anu.edu.au>  padarn <padarn@wilsonp.anu.edu.au> 
+Padarn Wilson <padarn@gmail.com> Padarn <padarn@Padarns-MacBook-Air.local>
+Paris Sprint Account <paris@grf>  Paris Sprint Account <paris@grf> 
+Paul Hobson <pmhobson@gmail.com>  Paul Hobson <pmhobson@gmail.com> 
+Peter Prettenhofer <peter.prettenhofer@gmail.com>  Peter Prettenhofer <peter.prettenhofer@gmail.com> 
+Pietro Battiston <me@pietrobattiston.it>  Pietro Battiston <me@pietrobattiston.it> 
+Ralf Gommers <ralf.gommers@googlemail.com>  Ralf Gommers <ralf.gommers@googlemail.com> 
+Richard T. Guy <richardtguy84@gmail.com>  Richard T. Guy <richardtguy84@gmail.com> 
+Robert Cimrman <cimrman3@ntc.zcu.cz>  Robert Cimrman <cimrman3@ntc.zcu.cz> 
+Roger Lew <rogerlew@gmail.com>  Roger Lew <rogerlew@gmail.com> 
+scottpiraino <scottpiraino@gmail.com>  scottpiraino <scottpiraino@gmail.com> 
+sebastien.meriaux <>  sebastien.meriaux <> 
+Skipper Seabold <jsseabold@gmail.com>  jsseabold <> 
+Skipper Seabold <jsseabold@gmail.com>  jsseabold <jsseabold@gmail.com> 
+Skipper Seabold <jsseabold@gmail.com>  Skipper Seabold <jsseabold@gmail.com> 
+skipper seabold <skipper@linux-laptop>  skipper seabold <skipper@linux-laptop> 
+Skipper Seabold <jsseabold@gmail.com>  skipper <skipper@linux-desktop> 
+Skipper Seabold <jsseabold@gmail.com>  skipper <skipper@linux-econ2> 
+Steve Genoud <sgenoud@ethz.ch>  Steve Genoud <sgenoud@ethz.ch> 
+Thomas Haslwanter <thomas.haslwanter@fh-linz.at>  Thomas Haslwanter <thomas.haslwanter@fh-linz.at> 
+Thomas Kluyver <takowl@gmail.com>  Thomas Kluyver <takowl@gmail.com> 
+tim.leslie <>  tim.leslie <> 
+timmie <timmichelsen@gmx-topmail.de>  timmie <timmichelsen@gmx-topmail.de> 
+Tom Augspurger <thomas-augspurger@uiowa.edu>  TomAugspurger <thomas-augspurger@uiowa.edu> 
+Tom Augspurger <thomas-augspurger@uiowa.edu> Tom Augspurger <tom.augspurger88@gmail.com>
+Tom Waite <twaite@berkeley.edu>  Tom Waite <twaite@berkeley.edu> 
+Tom Waite <twaite@berkeley.edu>  twaite <twaite@TOM-DUAL> 
+Trent Hauck <trent.hauck@gmail.com>  Trent Hauck <trent.hauck@gmail.com> 
+Trent Hauck <trent.hauck@gmail.com>  tshauck <trent.hauck@gmail.com> 
+tylerhartley <tyleha@gmail.com>  tylerhartley <tyleha@gmail.com> 
+Vincent Arel-Bundock <varel@umich.edu>  Vincent Arel-Bundock <varel@umich.edu> 
+Vincent Davis <vincent@vincentdavis.net>  Vincent Davis <vincent@vincentdavis.net> 
+VirgileFritsch <virgile.fritsch@gmail.com>  VirgileFritsch <virgile.fritsch@gmail.com> 
+Wes McKinney <wesmckinn@gmail.com>  Wes McKinney <wesmckinn@gmail.com> 
+Wes McKinney <wesmckinn@gmail.com>  Wes McKinney <wesm@wesm-desktop> 
+Yaroslav Halchenko <debian@onerussian.com>  Yaroslav Halchenko <debian@onerussian.com> 
+zed <arn.zart+github@gmail.com>  zed <arn.zart+github@gmail.com> 

statsmodels/source/.pep8speaks.yml

@@ -0,0 +1,9 @@
+scanner:
+    diff_only: True
+    linter: flake8
+
+flake8:
+    max-line-length: 79
+    ignore:  # Errors and warnings to ignore
+        - W503
+        - W504

statsmodels/source/CHANGES.md

@@ -0,0 +1,4 @@
+Release Notes
+=============
+
+The list of changes for each statsmodels release can be found [here](https://www.statsmodels.org/devel/release/index.html). Full details are available in the [commit logs](https://github.com/statsmodels/statsmodels).

statsmodels/source/CITATION.cff

@@ -0,0 +1,38 @@
+cff-version: 1.2.0
+title: statsmodels
+message: >-
+  Please use following citation to cite statsmodels in
+  scientific publications
+type: software
+authors:
+  - given-names: Seabold
+    family-names: Skipper
+  - given-names: Perktold
+    family-names: Josef
+repository-code: 'https://github.com/statsmodels/statsmodels'
+url: 'https://www.statsmodels.org/'
+keywords:
+  - python
+  - data-science
+  - statistics
+  - prediction
+  - econometrics
+  - forecasting
+  - data-analysis
+  - regression-models
+  - hypothesis-testing
+  - generalized-linear-models
+  - timeseries-analysis
+  - robust-estimation
+  - count-model
+license: BSD-3-Clause
+preferred-citation:
+  type: article
+  authors:
+    - given-names: Seabold
+      family-names: Skipper
+    - given-names: Perktold
+      family-names: Josef
+  title: "statsmodels: Econometric and statistical modeling with python"
+  journal: "9th Python in Science Conference"
+  year: 2010

statsmodels/source/CONTRIBUTING.rst

@@ -0,0 +1,73 @@
+Contributing guidelines
+=======================
+
+This page explains how you can contribute to the development of `statsmodels`
+by submitting patches, statistical tests, new models, or examples.
+
+`statsmodels` is developed on `Github <https://github.com/statsmodels/statsmodels>`_
+using the `Git <https://git-scm.com/>`_ version control system.
+
+Submitting a Bug Report
+~~~~~~~~~~~~~~~~~~~~~~~
+
+- Include a short, self-contained code snippet that reproduces the problem
+- Specify the statsmodels version used. You can do this with ``sm.version.full_version``
+- If the issue looks to involve other dependencies, also include the output of ``sm.show_versions()``
+
+Making Changes to the Code
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For a pull request to be accepted, you must meet the below requirements. This greatly helps in keeping the job of maintaining and releasing the software a shared effort.
+
+- **One branch. One feature.** Branches are cheap and github makes it easy to merge and delete branches with a few clicks. Avoid the temptation to lump in a bunch of unrelated changes when working on a feature, if possible. This helps us keep track of what has changed when preparing a release.
+- Commit messages should be clear and concise. This means a subject line of less than 80 characters, and, if necessary, a blank line followed by a commit message body. We have an `informal commit format standard <https://www.statsmodels.org/devel/dev/maintainer_notes.html#commit-comments>`_ that we try to adhere to. You can see what this looks like in practice by ``git log --oneline -n 10``. If your commit references or closes a specific issue, you can close it by mentioning it in the `commit message <https://help.github.com/articles/closing-issues-via-commit-messages>`_.  (*For maintainers*: These suggestions go for Merge commit comments too. These are partially the record for release notes.)
+- Code submissions must always include tests. See our `notes on testing <https://www.statsmodels.org/devel/dev/test_notes.html>`_.
+- Each function, class, method, and attribute needs to be documented using docstrings. We conform to the `numpy docstring standard <https://numpydoc.readthedocs.io/en/latest/format.html#docstring-standard>`_.
+- If you are adding new functionality, you need to add it to the documentation by editing (or creating) the appropriate file in ``docs/source``.
+- Make sure your documentation changes parse correctly. Change into the top-level ``docs/`` directory and type::
+
+   make clean
+   make html
+
+  Check that the build output does not have *any* warnings due to your changes.
+- Finally, please add your changes to the release notes. Open the ``docs/source/release/versionX.X.rst`` file that has the version number of the next release and add your changes to the appropriate section.
+
+Linting
+~~~~~~~
+
+Due to the way we have the CI builds set up, the linter will not do anything unless the environmental variable $LINT is set to a truthy value.
+
+- On MacOS/Linux
+
+    LINT=true ./lint.sh
+
+- Dependencies: flake8, git
+
+How to Submit a Pull Request
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+So you want to submit a patch to `statsmodels` but are not too familiar with github? Here are the steps you need to take.
+
+1. `Fork <https://help.github.com/articles/fork-a-repo>`_ the `statsmodels repository <https://github.com/statsmodels/statsmodels>`_ on Github.
+2. `Create a new feature branch <https://git-scm.com/book/en/Git-Branching-Basic-Branching-and-Merging>`_. Each branch must be self-contained, with a single new feature or bugfix.
+3. Make sure the test suite passes. This includes testing on Python 3. The easiest way to do this is to make a pull request and let the bot check for you. This can be slow, and if you are unsure about the fix or enhancement, it is best to run pytest locally.
+4. Document your changes by editing the appropriate file in ``docs/source/``. If it is a big, new feature add a note and an example to the latest ``docs/source/release/versionX.X.rst`` file. See older versions for examples. If it's a minor change, it will be included automatically in our release notes.
+5. Add an example. If it is a big, new feature please submit an example notebook by following `these instructions <https://www.statsmodels.org/devel/dev/examples.html>`_.
+6. `Submit a pull request <https://help.github.com/articles/using-pull-requests>`_
+
+Mailing List
+~~~~~~~~~~~~
+
+Conversations about development take place on the `statsmodels mailing list <https://groups.google.com/group/pystatsmodels?hl=en>`__.
+
+Learn More
+~~~~~~~~~~
+
+The ``statsmodels`` documentation's `developer page <https://www.statsmodels.org/stable/dev/index.html>`_
+offers much more detailed information about the process.
+
+License
+~~~~~~~
+
+statsmodels is released under the
+`Modified (3-clause) BSD license <https://www.opensource.org/licenses/BSD-3-Clause>`_.

statsmodels/source/COPYRIGHTS.txt

@@ -0,0 +1,249 @@
+
+The license of statsmodels can be found in LICENSE.txt
+
+statsmodels contains code or derivative code from several other
+packages. Some modules also note the author of individual contributions, or
+author of code that formed the basis for the derived or translated code.
+The copyright statements for the datasets are attached to the individual
+datasets, most datasets are in public domain, and we do not claim any copyright
+on any of them.
+
+In the following, we collect copyright statements of code from other packages,
+all of which are either a version of BSD or MIT licensed:
+
+numpy
+scipy
+pandas
+matplotlib
+scikit-learn
+qsturng-py http://code.google.com/p/qsturng-py/
+
+
+numpy (statsmodels.compatnp contains copy of entire model)
+----------------------------------------------------------
+Copyright (c) 2005-2009, NumPy Developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+       notice, this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above
+       copyright notice, this list of conditions and the following
+       disclaimer in the documentation and/or other materials provided
+       with the distribution.
+
+    * Neither the name of the NumPy Developers nor the names of any
+       contributors may be used to endorse or promote products derived
+       from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+---------------------------------------------------------------------
+
+scipy
+-----
+Copyright (c) 2001, 2002 Enthought, Inc.
+All rights reserved.
+
+Copyright (c) 2003-2009 SciPy Developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+  a. Redistributions of source code must retain the above copyright notice,
+     this list of conditions and the following disclaimer.
+  b. Redistributions in binary form must reproduce the above copyright
+     notice, this list of conditions and the following disclaimer in the
+     documentation and/or other materials provided with the distribution.
+  c. Neither the name of the Enthought nor the names of its contributors
+     may be used to endorse or promote products derived from this software
+     without specific prior written permission.
+
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGE.
+---------------------------------------------------------------------------
+
+
+pandas
+------
+
+Copyright (c) 2008-2009 AQR Capital Management, LLC
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+    * Redistributions of source code must retain the above copyright
+       notice, this list of conditions and the following disclaimer.
+
+    * Redistributions in binary form must reproduce the above
+       copyright notice, this list of conditions and the following
+       disclaimer in the documentation and/or other materials provided
+       with the distribution.
+
+    * Neither the name of the copyright holder nor the names of any
+       contributors may be used to endorse or promote products derived
+       from this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDER AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+----------------------------------------------------------------------
+
+
+matplotlib (copied from license.py)
+-----------------------------------
+
+
+LICENSE AGREEMENT FOR MATPLOTLIB %(version)s
+--------------------------------------
+
+1. This LICENSE AGREEMENT is between John D. Hunter ("JDH"), and the
+Individual or Organization ("Licensee") accessing and otherwise using
+matplotlib software in source or binary form and its associated
+documentation.
+
+2. Subject to the terms and conditions of this License Agreement, JDH
+hereby grants Licensee a nonexclusive, royalty-free, world-wide license
+to reproduce, analyze, test, perform and/or display publicly, prepare
+derivative works, distribute, and otherwise use matplotlib %(version)s
+alone or in any derivative version, provided, however, that JDH's
+License Agreement and JDH's notice of copyright, i.e., "Copyright (c)
+2002-%(year)d John D. Hunter; All Rights Reserved" are retained in
+matplotlib %(version)s alone or in any derivative version prepared by
+Licensee.
+
+3. In the event Licensee prepares a derivative work that is based on or
+incorporates matplotlib %(version)s or any part thereof, and wants to
+make the derivative work available to others as provided herein, then
+Licensee hereby agrees to include in any such work a brief summary of
+the changes made to matplotlib %(version)s.
+
+4. JDH is making matplotlib %(version)s available to Licensee on an "AS
+IS" basis. JDH MAKES NO REPRESENTATIONS OR WARRANTIES, EXPRESS OR
+IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, JDH MAKES NO AND
+DISCLAIMS ANY REPRESENTATION OR WARRANTY OF MERCHANTABILITY OR FITNESS
+FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF MATPLOTLIB %(version)s
+WILL NOT INFRINGE ANY THIRD PARTY RIGHTS.
+
+5. JDH SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF MATPLOTLIB
+%(version)s FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL DAMAGES OR
+LOSS AS A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING
+MATPLOTLIB %(version)s, OR ANY DERIVATIVE THEREOF, EVEN IF ADVISED OF
+THE POSSIBILITY THEREOF.
+
+6. This License Agreement will automatically terminate upon a material
+breach of its terms and conditions.
+
+7. Nothing in this License Agreement shall be deemed to create any
+relationship of agency, partnership, or joint venture between JDH and
+Licensee. This License Agreement does not grant permission to use JDH
+trademarks or trade name in a trademark sense to endorse or promote
+products or services of Licensee, or any third party.
+
+8. By copying, installing or otherwise using matplotlib %(version)s,
+Licensee agrees to be bound by the terms and conditions of this License
+Agreement.
+--------------------------------------------------------------------------
+
+scikits-learn
+-------------
+
+New BSD License
+
+Copyright (c) 2007 - 2010 Scikit-Learn Developers.
+All rights reserved.
+
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+  a. Redistributions of source code must retain the above copyright notice,
+     this list of conditions and the following disclaimer.
+  b. Redistributions in binary form must reproduce the above copyright
+     notice, this list of conditions and the following disclaimer in the
+     documentation and/or other materials provided with the distribution.
+  c. Neither the name of the Scikit-learn Developers  nor the names of
+     its contributors may be used to endorse or promote products
+     derived from this software without specific prior written
+     permission.
+
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGE.
+---------------------------------------------------------------------------
+
+qsturng-py (code included in statsmodels.stats.libqsturng)
+--------------------------------------------------------------
+Copyright (c) 2011, Roger Lew [see LICENSE.txt]
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions
+are met:
+  * Redistributions of source code must retain the above copyright
+    notice, this list of conditions and the following disclaimer.
+  * Redistributions in binary form must reproduce the above
+    copyright notice, this list of conditions and the following
+    disclaimer in the documentation and/or other materials provided
+    with the distribution.
+  * Neither the name of the organizations affiliated with the
+    contributors or the names of its contributors themselves may be
+    used to endorse or promote products derived from this software
+    without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
+ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+----------------------------------------------------------

statsmodels/source/INSTALL.txt

@@ -0,0 +1,122 @@
+Dependencies
+------------
+
+python >= 3.9
+
+    www.python.org
+
+numpy >= 1.22
+
+    www.numpy.org
+
+scipy >= 1.7
+
+    www.scipy.org
+
+pandas >= 1.3
+
+    pandas.pydata.org
+
+patsy >= 0.5.5
+
+    patsy.readthedocs.org
+
+cython >= 0.29.33 and < 4.0.0
+
+    https://cython.org/
+
+    Cython is required if you are building the source from github. However,
+    if you have are building from source distribution archive then the 
+    generated C files are included and Cython is not necessary. Earlier
+    versions may be ok for earlier versions of Python.
+
+Optional Dependencies
+---------------------
+
+X-12-ARIMA or X-13ARIMA-SEATS
+
+    https://www.census.gov/srd/www/x13as/
+
+    If available, time-series analysis can be conducted using either 
+    X-12-ARIMA or the newer X-13ARIMA-SEATS. You should place the 
+    appropriate executable on your PATH or set the X12PATH or X13PATH 
+    environmental variable to take advantage.
+
+matplotlib >= 3
+
+    https://matplotlib.org/
+
+    Matplotlib is needed for plotting functionality and running many of the 
+    examples.
+
+sphinx >= 1.3
+
+    http://sphinx.pocoo.org/
+
+    Sphinx is used to build the documentation.
+
+pytest >= 6
+
+    http://readthedocs.org/docs/pytest/en/latest/
+
+    Pytest is needed to run the tests.
+
+IPython >= 6
+
+    Needed to build the docs.
+
+
+Installing
+----------
+
+To get the latest release using pip
+
+    python -m pip install statsmodels --upgrade-strategy only-if-needed
+
+The additional parameter pip --upgrade-strategy only-if-needed will ensure
+that dependencies, e.g. NumPy or pandas, are not upgraded unless required.
+
+Ubuntu/Debian
+-------------
+
+On Ubuntu you can get dependencies through:
+
+    sudo apt-get install python python-dev python-setuptools python-numpy python-scipy
+    python -m pip install cython pandas
+
+Alternatively, you can install from the NeuroDebian repository:
+
+    http://neuro.debian.net
+
+
+Installing from Source
+----------------------
+
+Download and extract the source distribution from PyPI or github
+
+    https://pypi.python.org/pypi/statsmodels
+    https://github.com/statsmodels/statsmodels/tags
+
+Or clone the bleeding edge code from our repository on github at
+
+    git clone git://github.com/statsmodels/statsmodels.git
+
+In the statsmodels directory do (with proper permissions)
+
+    python -m pip install .
+
+You will need a C compiler installed.
+
+Installing from Source on Windows
+---------------------------------
+
+See https://www.statsmodels.org/devel/install.html#windows.
+
+
+Documentation
+-------------
+
+You may find more information about the project and installation in our 
+documentation
+
+https://www.statsmodels.org/devel/install.html

statsmodels/source/LICENSE.txt

@@ -0,0 +1,34 @@
+Copyright (C) 2006, Jonathan E. Taylor
+All rights reserved.
+
+Copyright (c) 2006-2008 Scipy Developers.
+All rights reserved.
+
+Copyright (c) 2009-2018 statsmodels Developers.
+All rights reserved.
+
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+  a. Redistributions of source code must retain the above copyright notice,
+     this list of conditions and the following disclaimer.
+  b. Redistributions in binary form must reproduce the above copyright
+     notice, this list of conditions and the following disclaimer in the
+     documentation and/or other materials provided with the distribution.
+  c. Neither the name of statsmodels nor the names of its contributors
+     may be used to endorse or promote products derived from this software
+     without specific prior written permission.
+
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ARE DISCLAIMED. IN NO EVENT SHALL STATSMODELS OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+DAMAGE.

statsmodels/source/MANIFEST.in

@@ -0,0 +1,29 @@
+global-include *.csv *.py *.txt *.pyx *.pyx.in *.pxd *.pxi *.c *.h *.pkl
+include statsmodels/_version.py
+include MANIFEST.in
+include README.rst
+
+recursive-exclude build *
+recursive-exclude dist *
+recursive-exclude tools *
+
+graft statsmodels/datasets
+graft statsmodels/sandbox/regression/data
+graft statsmodels/sandbox/tests
+graft statsmodels/sandbox/tsa/examples
+recursive-include docs/source *
+exclude docs/source/generated/*
+recursive-include docs/sphinxext *
+recursive-include docs/themes *
+recursive-exclude docs/build *
+recursive-exclude docs/build/htmlhelp *
+include statsmodels/statsmodelsdoc.chm
+include docs/make.bat
+include docs/Makefile
+
+recursive-include examples *
+
+prune */__pycache__
+
+global-exclude *~ *.swp  *.pyc *.pyo *.bak
+include statsmodels/_version.py

statsmodels/source/README.rst

@@ -0,0 +1,207 @@
+.. image:: docs/source/images/statsmodels-logo-v2-horizontal.svg
+  :alt: Statsmodels logo
+
+|PyPI Version| |Conda Version| |License| |Azure CI Build Status|
+|Codecov Coverage| |Coveralls Coverage| |PyPI downloads| |Conda downloads|
+
+About statsmodels
+=================
+
+statsmodels is a Python package that provides a complement to scipy for
+statistical computations including descriptive statistics and estimation
+and inference for statistical models.
+
+
+Documentation
+=============
+
+The documentation for the latest release is at
+
+https://www.statsmodels.org/stable/
+
+The documentation for the development version is at
+
+https://www.statsmodels.org/dev/
+
+Recent improvements are highlighted in the release notes
+
+https://www.statsmodels.org/stable/release/
+
+Backups of documentation are available at https://statsmodels.github.io/stable/
+and https://statsmodels.github.io/dev/.
+
+
+Main Features
+=============
+
+* Linear regression models:
+
+  - Ordinary least squares
+  - Generalized least squares
+  - Weighted least squares
+  - Least squares with autoregressive errors
+  - Quantile regression
+  - Recursive least squares
+
+* Mixed Linear Model with mixed effects and variance components
+* GLM: Generalized linear models with support for all of the one-parameter
+  exponential family distributions
+* Bayesian Mixed GLM for Binomial and Poisson
+* GEE: Generalized Estimating Equations for one-way clustered or longitudinal data
+* Discrete models:
+
+  - Logit and Probit
+  - Multinomial logit (MNLogit)
+  - Poisson and Generalized Poisson regression
+  - Negative Binomial regression
+  - Zero-Inflated Count models
+
+* RLM: Robust linear models with support for several M-estimators.
+* Time Series Analysis: models for time series analysis
+
+  - Complete StateSpace modeling framework
+
+    - Seasonal ARIMA and ARIMAX models
+    - VARMA and VARMAX models
+    - Dynamic Factor models
+    - Unobserved Component models
+
+  - Markov switching models (MSAR), also known as Hidden Markov Models (HMM)
+  - Univariate time series analysis: AR, ARIMA
+  - Vector autoregressive models, VAR and structural VAR
+  - Vector error correction model, VECM
+  - exponential smoothing, Holt-Winters
+  - Hypothesis tests for time series: unit root, cointegration and others
+  - Descriptive statistics and process models for time series analysis
+
+* Survival analysis:
+
+  - Proportional hazards regression (Cox models)
+  - Survivor function estimation (Kaplan-Meier)
+  - Cumulative incidence function estimation
+
+* Multivariate:
+
+  - Principal Component Analysis with missing data
+  - Factor Analysis with rotation
+  - MANOVA
+  - Canonical Correlation
+
+* Nonparametric statistics: Univariate and multivariate kernel density estimators
+* Datasets: Datasets used for examples and in testing
+* Statistics: a wide range of statistical tests
+
+  - diagnostics and specification tests
+  - goodness-of-fit and normality tests
+  - functions for multiple testing
+  - various additional statistical tests
+
+* Imputation with MICE, regression on order statistic and Gaussian imputation
+* Mediation analysis
+* Graphics includes plot functions for visual analysis of data and model results
+
+* I/O
+
+  - Tools for reading Stata .dta files, but pandas has a more recent version
+  - Table output to ascii, latex, and html
+
+* Miscellaneous models
+* Sandbox: statsmodels contains a sandbox folder with code in various stages of
+  development and testing which is not considered "production ready".  This covers
+  among others
+
+  - Generalized method of moments (GMM) estimators
+  - Kernel regression
+  - Various extensions to scipy.stats.distributions
+  - Panel data models
+  - Information theoretic measures
+
+How to get it
+=============
+The main branch on GitHub is the most up to date code
+
+https://www.github.com/statsmodels/statsmodels
+
+Source download of release tags are available on GitHub
+
+https://github.com/statsmodels/statsmodels/tags
+
+Binaries and source distributions are available from PyPi
+
+https://pypi.org/project/statsmodels/
+
+Binaries can be installed in Anaconda
+
+conda install statsmodels
+
+
+Getting the latest code
+=======================
+
+Installing the most recent nightly wheel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+The most recent nightly wheel can be installed using pip.
+
+.. code:: bash
+
+   python -m pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple statsmodels --upgrade --use-deprecated=legacy-resolver
+
+Installing from sources
+~~~~~~~~~~~~~~~~~~~~~~~
+
+See INSTALL.txt for requirements or see the documentation
+
+https://statsmodels.github.io/dev/install.html
+
+Contributing
+============
+Contributions in any form are welcome, including:
+
+* Documentation improvements
+* Additional tests
+* New features to existing models
+* New models
+
+https://www.statsmodels.org/stable/dev/test_notes
+
+for instructions on installing statsmodels in *editable* mode.
+
+License
+=======
+
+Modified BSD (3-clause)
+
+Discussion and Development
+==========================
+
+Discussions take place on the mailing list
+
+https://groups.google.com/group/pystatsmodels
+
+and in the issue tracker. We are very interested in feedback
+about usability and suggestions for improvements.
+
+Bug Reports
+===========
+
+Bug reports can be submitted to the issue tracker at
+
+https://github.com/statsmodels/statsmodels/issues
+
+.. |Azure CI Build Status| image:: https://dev.azure.com/statsmodels/statsmodels-testing/_apis/build/status/statsmodels.statsmodels?branchName=main
+   :target: https://dev.azure.com/statsmodels/statsmodels-testing/_build/latest?definitionId=1&branchName=main
+.. |Codecov Coverage| image:: https://codecov.io/gh/statsmodels/statsmodels/branch/main/graph/badge.svg
+   :target: https://codecov.io/gh/statsmodels/statsmodels
+.. |Coveralls Coverage| image:: https://coveralls.io/repos/github/statsmodels/statsmodels/badge.svg?branch=main
+   :target: https://coveralls.io/github/statsmodels/statsmodels?branch=main
+.. |PyPI downloads| image:: https://img.shields.io/pypi/dm/statsmodels?label=PyPI%20Downloads
+   :alt: PyPI - Downloads
+   :target: https://pypi.org/project/statsmodels/
+.. |Conda downloads| image:: https://img.shields.io/conda/dn/conda-forge/statsmodels.svg?label=Conda%20downloads
+   :target: https://anaconda.org/conda-forge/statsmodels/
+.. |PyPI Version| image:: https://img.shields.io/pypi/v/statsmodels.svg
+   :target: https://pypi.org/project/statsmodels/
+.. |Conda Version| image:: https://anaconda.org/conda-forge/statsmodels/badges/version.svg
+   :target: https://anaconda.org/conda-forge/statsmodels/
+.. |License| image:: https://img.shields.io/pypi/l/statsmodels.svg
+   :target: https://github.com/statsmodels/statsmodels/blob/main/LICENSE.txt

statsmodels/source/README_l1.txt

@@ -0,0 +1,40 @@
+What the l1 addition is
+=======================
+A slight modification that allows l1 regularized LikelihoodModel.
+
+Regularization is handled by a fit_regularized method.
+
+Main Files
+==========
+
+l1_demo/demo.py
+    $ python demo.py --get_l1_slsqp_results logit
+    does a quick demo of the regularization using logistic regression.
+
+l1_demo/sklearn_compare.py
+    $ python sklearn_compare.py
+    Plots a comparison of regularization paths.  Modify the source to use
+    different datasets.
+
+statsmodels/base/l1_cvxopt.py
+    fit_l1_cvxopt_cp()
+        Fit likelihood model using l1 regularization.  Use the CVXOPT package.
+    Lots of small functions supporting fit_l1_cvxopt_cp
+
+statsmodels/base/l1_slsqp.py
+    fit_l1_slsqp()
+        Fit likelihood model using l1 regularization.  Use scipy.optimize
+    Lots of small functions supporting fit_l1_slsqp
+
+statsmodels/base/l1_solvers_common.py
+    Common methods used by l1 solvers
+
+statsmodels/base/model.py
+    Likelihoodmodel.fit()
+        3 lines modified to allow for importing and calling of l1 fitting functions
+
+statsmodels/discrete/discrete_model.py
+    L1MultinomialResults class
+        Child of MultinomialResults
+    MultinomialModel.fit()
+        3 lines re-directing l1 fit results to the L1MultinomialResults class

statsmodels/source/__init__.py

@@ -0,0 +1,4 @@
+# -*- coding: utf-8 -*-
+"""
+statsmodels Project Package Initialization File
+"""

statsmodels/source/archive/README.md

@@ -0,0 +1,15 @@
+# Deprecated Legacy Code Archive
+
+This directory contains historical code that was previously part of  
+statsmodels but is **no longer maintained or supported**.
+
+## Purpose
+- Preserve Git history for reference  
+- Maintain backward compatibility in version control  
+
+## Important Notes
+⚠️ **Do not use** these files in production  
+⚠️ Code is provided **as-is** without maintenance  
+⚠️ No bug fixes or security updates will be provided  
+
+For current implementations, please refer to the active codebase.

statsmodels/source/archive/docs/GLMNotes.lyx

@@ -0,0 +1,1155 @@
+#LyX 1.6.2 created this file. For more info see http://www.lyx.org/
+\lyxformat 345
+\begin_document
+\begin_header
+\textclass article
+\use_default_options true
+\language english
+\inputencoding auto
+\font_roman default
+\font_sans default
+\font_typewriter default
+\font_default_family default
+\font_sc false
+\font_osf false
+\font_sf_scale 100
+\font_tt_scale 100
+
+\graphics default
+\paperfontsize default
+\spacing single
+\use_hyperref false
+\papersize default
+\use_geometry true
+\use_amsmath 1
+\use_esint 1
+\cite_engine basic
+\use_bibtopic false
+\paperorientation portrait
+\leftmargin 1in
+\topmargin 1in
+\rightmargin 1in
+\bottommargin 1in
+\secnumdepth 3
+\tocdepth 3
+\paragraph_separation indent
+\defskip medskip
+\quotes_language english
+\papercolumns 1
+\papersides 1
+\paperpagestyle default
+\tracking_changes false
+\output_changes false
+\author "" 
+\author "" 
+\end_header
+
+\begin_body
+
+\begin_layout Standard
+Variance Functions:
+\end_layout
+
+\begin_layout Standard
+Constant: 
+\begin_inset Formula $\boldsymbol{1}$
+\end_inset
+
+
+\end_layout
+
+\begin_layout Standard
+Power: 
+\begin_inset Formula $\boldsymbol{X}^{2}$
+\end_inset
+
+
+\end_layout
+
+\begin_layout Standard
+Binomial: 
+\begin_inset Formula $np(1-p)\text{ where }p=\frac{\mu}{n};\,\, V(\mu)=np(1-p)$
+\end_inset
+
+
+\end_layout
+
+\begin_layout Standard
+\begin_inset Formula $\frac{\partial\mu}{\partial\eta}$
+\end_inset
+
+
+\end_layout
+
+\begin_layout Standard
+Links: initialization of base class returns the actual mean vector
+\begin_inset Formula $\boldsymbol{\mu}$
+\end_inset
+
+; 
+\begin_inset Formula $p$
+\end_inset
+
+ in the logit and subclasses; 
+\begin_inset Formula $x$
+\end_inset
+
+ elsewhere.
+\end_layout
+
+\begin_layout Standard
+\begin_inset Float table
+placement H
+wide false
+sideways false
+status open
+
+\begin_layout Plain Layout
+\begin_inset Tabular
+<lyxtabular version="3" rows="11" columns="4">
+<features>
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Link 
+\begin_inset Formula $g(p)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Inverse 
+\begin_inset Formula $g^{-1}(p)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Analytic Derivative 
+\begin_inset Formula $g^{\prime}(p)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Logit
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $z=\log\frac{p}{1-p}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $p=\frac{e^{z}}{1+e^{z}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $g^{\prime}(p)=\frac{1}{p(1-p)}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Power
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $z=x^{\text{pow}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $x=z^{\frac{1}{\text{pow}}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $g^{\prime}(x)=\text{pow}\cdot x^{\text{power}-1}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Inverse
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="1" alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+same as above with 
+\begin_inset Formula $\text{pow}=-1$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Square Root
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="1" alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\text{pow}=0.5$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Identity
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="1" alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\text{pow}=1$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" bottomline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Log
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $z=\log x$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $g^{-1}(z)=e^{z}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $g^{\prime}(x)=\frac{1}{x}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+CDFLink/Probit
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $z=\Phi^{-1}(p)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $p=\Phi(z)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $g^{\prime}(x)=\frac{1}{\int_{-\infty}^{p}f(t)dt}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Cauchy
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="1" alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+same as the above with the Cauchy distribution
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" bottomline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell multicolumn="2" alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+CLogLog
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $z=\log(-\log p)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $p=e^{-e^{z}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $g^{\prime}(p)=-\frac{1}{p\log p}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+</lyxtabular>
+
+\end_inset
+
+
+\end_layout
+
+\begin_layout Plain Layout
+\begin_inset Caption
+
+\begin_layout Plain Layout
+Link Functions
+\end_layout
+
+\end_inset
+
+
+\end_layout
+
+\end_inset
+
+
+\end_layout
+
+\begin_layout Standard
+Initializing the family sets a link property and a variance based on the
+ link(?)
+\end_layout
+
+\begin_layout Standard
+\begin_inset Float table
+placement H
+wide false
+sideways false
+status open
+
+\begin_layout Plain Layout
+\begin_inset Tabular
+<lyxtabular version="3" rows="8" columns="6">
+<features>
+<column alignment="center" valignment="top" width="0.75in">
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<column alignment="center" valignment="top" width="0">
+<row>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Family
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Weights
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Deviance
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+DevResid
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Fitted
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Predict
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Base Class
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\frac{1}{(g^{\prime}(\mu))^{2}\cdot V(\mu)}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\frac{\sum_{i}\text{DevResid}^{2}}{\text{scale}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\left(Y-\mu\right)\cdot\sqrt{\text{weights}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\mu=g^{-1}(\eta)$
+\end_inset
+
+*
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\eta=g(\mu)$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Poisson
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\text{sign}\left(Y-\mu\right)\sqrt{2Y\log\frac{Y}{\mu}-2(Y-\mu)}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Gaussian
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\frac{\left(Y-\mu\right)}{\text{\sqrt{\text{scale}\cdot V\left(\mu\right)}}}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Gamma
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Bug?
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Binomial
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+\begin_inset Formula $\text{sign}\left(Y-\mu\right)\sqrt{-2Y\log\frac{\mu}{n}+\left(n-Y\right)\log\left(1-\frac{\mu}{n}\right)}$
+\end_inset
+
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+Inverse Gaussian
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+?
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+<row>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+<cell alignment="center" valignment="top" topline="true" bottomline="true" leftline="true" rightline="true" usebox="none">
+\begin_inset Text
+
+\begin_layout Plain Layout
+
+\end_layout
+
+\end_inset
+</cell>
+</row>
+</lyxtabular>
+
+\end_inset
+
+
+\end_layout
+
+\begin_layout Plain Layout
+\begin_inset Caption
+
+\begin_layout Plain Layout
+Families
+\end_layout
+
+\end_inset
+
+
+\end_layout
+
+\begin_layout Plain Layout
+* 
+\begin_inset Formula $\eta$
+\end_inset
+
+ is the linear predictor ie., 
+\begin_inset Formula $X\beta$
+\end_inset
+
+ in the generalized linear model
+\end_layout
+
+\end_inset
+
+
+\end_layout
+
+\end_body
+\end_document

statsmodels/source/archive/docs/fix_longtable.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+import sys
+import os
+
+
+BUILDDIR = sys.argv[-1]
+read_file_path = os.path.join(BUILDDIR,'latex','statsmodels.tex')
+write_file_path = os.path.join(BUILDDIR, 'latex','statsmodels_tmp.tex')
+
+read_file = open(read_file_path, encoding="utf-8")
+write_file = open(write_file_path, 'w', encoding="utf-8")
+
+for line in read_file:
+    if 'longtable}{LL' in line:
+        line = line.replace('longtable}{LL', 'longtable}{|l|l|')
+    write_file.write(line)
+
+read_file.close()
+write_file.close()
+
+os.remove(read_file_path)
+os.rename(write_file_path, read_file_path)

statsmodels/source/archive/tsa/ex_arma.py

@@ -0,0 +1,99 @@
+'''
+
+does not seem to work so well anymore even with nobs=1000 ???
+works ok if noise variance is large
+'''
+
+import numpy as np
+import statsmodels.api as sm
+from statsmodels.tsa.arima_process import arma_generate_sample
+from statsmodels.tsa.arma_mle import Arma as Arma
+from statsmodels.tsa.arima_process import ARIMA as ARIMA_old
+from statsmodels.sandbox.tsa.garch import Arma as Armamle_old
+
+
+print("\nExample 1")
+ar = [1.0,  -0.6, 0.1]
+ma = [1.0,  0.5, 0.3]
+nobs = 1000
+y22 = arma_generate_sample(ar, ma, nobs+1000, 0.5)[-nobs:]
+y22 -= y22.mean()
+start_params = [0.1, 0.1, 0.1, 0.1]
+start_params_lhs = [-0.1, -0.1, 0.1, 0.1]
+
+print('truelhs', np.r_[ar[1:], ma[1:]])
+
+
+
+
+
+###bug in current version, fixed in Skipper and 1 more
+###arr[1:q,:] = params[p+k:p+k+q]  # p to p+q short params are MA coeffs
+###ValueError: array dimensions are not compatible for copy
+##from statsmodels.tsa.arima import ARMA as ARMA_kf
+##arma22 = ARMA_kf(y22, constant=False, order=(2,2))
+##res = arma22.fit(start_params=start_params)
+##print res.params
+
+print('\nARIMA new')
+arest2 = Arma(y22)
+
+naryw = 4  #= 30
+resyw = sm.regression.yule_walker(y22, order=naryw, inv=True)
+arest2.nar = naryw
+arest2.nma = 0
+e = arest2.geterrors(np.r_[1, -resyw[0]])
+x=sm.tsa.tsatools.lagmat2ds(np.column_stack((y22,e)),3,dropex=1,
+                            trim='both')
+yt = x[:,0]
+xt = x[:,1:]
+res_ols = sm.OLS(yt, xt).fit()
+print('hannan_rissannen')
+print(res_ols.params)
+start_params = res_ols.params
+start_params_mle = np.r_[-res_ols.params[:2],
+                          res_ols.params[2:],
+                          #res_ols.scale]
+                          #areste.var()]
+                          np.sqrt(res_ols.scale)]
+#need to iterate, ar1 too large ma terms too small
+#fix large parameters, if hannan_rissannen are too large
+start_params_mle[:-1] = (np.sign(start_params_mle[:-1])
+                         * np.minimum(np.abs(start_params_mle[:-1]),0.75))
+
+
+print('conditional least-squares')
+
+#print rhohat2
+print('with mle')
+arest2.nar = 2
+arest2.nma = 2
+#
+res = arest2.fit_mle(start_params=start_params_mle, method='nm') #no order in fit
+print(res.params)
+rhohat2, cov_x2a, infodict, mesg, ier = arest2.fit((2,2))
+print('\nARIMA_old')
+arest = ARIMA_old(y22)
+rhohat1, cov_x1, infodict, mesg, ier = arest.fit((2,0,2))
+print(rhohat1)
+print(np.sqrt(np.diag(cov_x1)))
+err1 = arest.errfn(x=y22)
+print(np.var(err1))
+print('bse ls, formula  not checked')
+print(np.sqrt(np.diag(cov_x1))*err1.std())
+print('bsejac for mle')
+#print arest2.bsejac
+#TODO:check bsejac raises singular matrix linalg error
+#in model.py line620: return np.linalg.inv(np.dot(jacv.T, jacv))
+
+print('\nyule-walker')
+print(sm.regression.yule_walker(y22, order=2, inv=True))
+
+print('\nArmamle_old')
+arma1 = Armamle_old(y22)
+arma1.nar = 2
+arma1.nma = 2
+#arma1res = arma1.fit(start_params=np.r_[-0.5, -0.1, 0.1, 0.1, 0.5], method='fmin')
+#                     maxfun=1000)
+arma1res = arma1.fit(start_params=res.params*0.7, method='fmin')
+print(arma1res.params)

statsmodels/source/archive/tsa/notes_organize.txt

@@ -0,0 +1,227 @@
+
+
+
+scikits.statsmodels.sandbox.tsa.kalmanf
+---------------------------------------
+ARMA  :      ARMA model using the exact Kalman Filter
+StateSpaceModel  :
+kalmanfilter  :      Returns the negative log-likelihood of y
+conditional on the information set
+kalmansmooth  :
+updatematrices  :      TODO: change API, update names
+
+
+scikits.statsmodels.sandbox.tsa.arima
+-------------------------------------
+
+runs ok, no refactoring bugs
+has examples and monte carlo that can be split up into example files
+
+ARIMA  :  currently ARMA only, no differencing used - no I
+arma2ar  :  get the AR representation of an ARMA process
+arma2ma  :  get the impulse response function (MA representation) for
+ARMA process
+arma_acf  :  theoretical autocovariance function of ARMA process
+arma_acovf  :  theoretical autocovariance function of ARMA process
+arma_generate_sample  :  generate an random sample of an ARMA process
+arma_impulse_response  :  get the impulse response function (MA
+representation) for ARMA process
+arma_pacf  :  partial autocorrelation function of an ARMA process
+deconvolve  :  Deconvolves divisor out of signal, division of
+polynomials for n terms
+index2lpol  :  expand coefficients to lag poly
+lpol2index  :  remove zeros from lagpolynomial, squeezed
+representation with index
+mcarma22  :  run Monte Carlo for ARMA(2,2)
+
+
+scikits.statsmodels.sandbox.tsa.varma
+-------------------------------------
+
+just filter experiments
+needed to fix import for acf example
+
+VAR  :   multivariate linear filter
+VARMA  :   multivariate linear filter
+
+scikits.statsmodels.sandbox.tsa.varma_tools
+-------------------------------------------
+
+Helper and filter functions for VAR and VARMA, and basic VAR class
+needed import fix in top of module
+maybe rename to varma_process
+in "main" example for VarmaPoly, and some Var fit
+Var could be used for Granger Causality tests, otherwise it's pretty limited
+
+Var  :
+    simultaneous OLS estimation
+VarmaPoly  :  class to keep track of Varma polynomial format
+    working with and transforming VARMA Lag-Polynomials (3d)
+ar2full  :  make reduced lagpolynomial into a right side lagpoly array
+ar2lhs  :  convert full (rhs) lagpolynomial into a reduced, left side
+lagpoly array
+padone  :  pad with zeros along one axis, currently only axis=0
+trimone  :  trim number of array elements along one axis
+varfilter  :  apply an autoregressive filter to a series x
+vargenerate  :  generate an VAR process with errors u
+varinversefilter  :  creates inverse ar filter (MA representation) recursively
+
+
+scikits.statsmodels.sandbox.tsa.try_fi
+--------------------------------------
+
+(not included by script that generates this list)
+various functions to build lag-polynomials for fractional and seasonal integration
+and function ar2arma minimizes distance in terms of impulse response function
+
+move these to a module or rename
+
+scikits.statsmodels.sandbox.tsa.try_var_convolve.py
+---------------------------------------------------
+
+(not included by script that generates this list)
+two functions:
+arfilter : autoregressive filter for 1d, 2d and 3d
+fftconvolve : multidimensional filtering using fft
+
+many examples, but I'm not sure this (fft) is correct
+incompletely copied for interpreter session
+currently raises exception because a variable (imp) is not defined
+
+scikits.statsmodels.sandbox.tsa.try_var_convolve.py
+---------------------------------------------------
+
+(not included by script that generates this list)
+includes functions for
+detrending,
+(theoretical) acovf and similar for special cases
+acf plot functions
+
+(partially copied from matplotlib.mlab)
+
+currently exception:  FIXED
+uses arima.ARIMA class without data in constructor, and order now has 3 values and
+is keyword with tuple as value
+
+move plot function to new graphics directory ?
+
+
+scikits.statsmodels.sandbox.regression.mle
+------------------------------------------
+
+one refactoring bug fixed, because arima.ARIMA needs data, use class method instead
+runs without exception, but I did not look at any results
+"main" has quite a lot
+
+AR  :      Notes
+Arma  :      univariate Autoregressive Moving Average model
+Garch  :  Garch model gjrgarch (t-garch)
+Garch0  :  Garch model,
+GarchX  :  Garch model,
+LikelihoodModel  :      Likelihood model is a subclass of Model.
+TSMLEModel  :      univariate time series model for estimation with
+maximum likelihood
+garchplot  :
+generate_garch  :  simulate standard garch
+generate_gjrgarch  :  simulate gjr garch process
+generate_kindofgarch  :  simulate garch like process but not squared
+errors in arma
+gjrconvertparams  :      flat to matrix
+loglike_GARCH11  :
+miso_lfilter  :      use nd convolution to merge inputs,
+normloglike  :
+test_gjrgarch  :
+test_misofilter  :
+
+Other
+-----
+diffusion: continuous time processes, produce nice graphs but parameterization is
+a bit inconsistent.
+
+
+script files
+============
+
+sandbox/tsa/try_arma_more.py
+----------------------------
+
+imports scikits.talkbox which is not compiled against my current numpy and does not
+run
+contains
+arma_periodogram : theoretical periodogram
+
+
+Proposed Structure (preliminary)
+================================
+
+arima_estimation
+----------------
+ARIMA class for estimation, wrapper or containing different estimators
+other wrappers: here or in separate ???
+  - support for choosing lag-length
+
+
+arma_process
+------------
+all theoretical properties for given parameters
+simulation method with options: initial conditions, errors, (?) not sure what else
+
+varma_process
+-------------
+including VarmaPoly and impulse response functions
+
+filters
+-------
+miso_filter (should be in cython eventually)
+ar_filter : fast VAR filter with convolution or fft convolution
+(not sure what's the relationship between the two)
+others ???
+
+stattools
+---------
+empirical properties
+acf, ...
+
+tsatools
+--------
+helper functions
+lagmat
+detrend ???
+
+others, unclear
+---------------
+???
+
+open questions
+==============
+
+support for exog
+----------------
+is incomplete or missing from some implementations
+not clear parameterization
+- ARMAX  A(L)y_t = C(L)x_t + B(L)e_t
+- ARMAX-simple  A(L)y_t = beta x_t + B(L)e_t
+  Note: covers previous version by extending x_t
+
+- ARMA residuals y_t = beta x_t + u_t, and A(L)u_t = B(L)e_t
+- ARMAX 2-step A(L)(y_t - beta x_t) = B(L)e_t
+  Note: looks the same as ARMA residuals, implies
+      A(L)y_t = A(L)x_t + B(L)e_t
+
+- ARMAX  A(L)(y_t - A^{-1}(L) C(L) x_t) = B(L)e_t
+  this does not look useful, unless we cutoff A^{-1}(L)
+
+problem: signal.lfilter can only handle ARMAX residuals model (I think)
+deterministic trend have ARMAX-simple model, e.g. in unit root tests
+
+
+support for seasonal and "sparse" lag-polynomials
+-------------------------------------------------
+- fit functions need support for different lag structures,
+  e.g. zeros, multiplicative
+- support for pre-filters, e.g. (seasonal) differencing
+
+
+
+
+

statsmodels/source/azure-pipelines.yml

@@ -0,0 +1,36 @@
+# https://docs.microsoft.com/en-us/azure/devops/pipelines/process/templates?view=azure-devops#passing-parameters
+
+trigger:
+- main
+schedules:
+- cron: "0 6 * * 1"   # Each Monday at 06:00 UTC
+  displayName: Weekly scheduled run
+  branches:
+    include: [main, maintenance/0.13.x]
+  always: true
+
+variables:
+  MKL_NUM_THREADS: 1
+  NUMEXPR_NUM_THREADS: 1
+  OMP_NUM_THREADS: 1
+  VML_NUM_THREADS: 1
+  OPENBLAS_NUM_THREADS: 1
+  PYTHONHASHSEED: 0 # Ensure tests are correctly gathered by xdist
+  USE_MATPLOTLIB: true
+
+jobs:
+
+- template: tools/ci/azure/azure_template_posix.yml
+  parameters:
+    name: Linux
+    vmImage: ubuntu-latest
+
+- template: tools/ci/azure/azure_template_posix.yml
+  parameters:
+    name: macOS
+    vmImage: macOS-latest
+
+- template: tools/ci/azure/azure_template_windows.yml
+  parameters:
+    name: Windows
+    vmImage: windows-latest

statsmodels/source/codecov.yml

@@ -0,0 +1,16 @@
+codecov:
+  branch: main
+  notify:
+    require_ci_to_pass: no
+    after_n_builds: 1
+
+comment: off
+
+coverage:
+  status:
+    project:
+      default:
+        target: '82'
+    patch:
+      default:
+        target: '50'

statsmodels/source/docs/Makefile

@@ -0,0 +1,44 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+PAPER         =
+TOOLSPATH	  = ../tools/
+DATASETBUILD  = dataset_rst.py
+NOTEBOOKBUILD = nbgenerate.py
+
+# Internal variables.
+PAPEROPT_a4     = -D latex_paper_size=a4
+PAPEROPT_letter = -D latex_paper_size=letter
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+html:
+    # make directories for images
+	@echo "Make static directory for images"
+	mkdir -p $(BUILDDIR)/html/_static
+	# generate the examples rst files
+	@echo "Generating datasets from installed statsmodels.datasets"
+	$(TOOLSPATH)$(DATASETBUILD)
+	@echo "Executing notebooks from examples/notebooks folder"
+	mkdir -p $(BUILDDIR)/source/examples/notebooks/generated
+	# Black list notebooks from doc build here
+	$(TOOLSPATH)$(NOTEBOOKBUILD) --parallel --report-errors --skip-existing --execute-only --execution-blacklist statespace_custom_models
+	@echo "Running sphinx-build"
+	@echo @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) $(O)
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) $(O)
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) $(O)

statsmodels/source/docs/README.md

@@ -0,0 +1,37 @@
+# Documentation Guidelines: Sphinx and Jupyter Notebooks Integration
+
+We use a combination of sphinx and Jupyter notebooks for the documentation.
+Jupyter notebooks should be used for longer, self-contained examples demonstrating
+a topic.
+Sphinx is nice because we get the tables of contents and API documentation.
+
+## Build Process
+
+Building the docs requires a few additional dependencies. You can get most
+of these with
+
+```bash
+
+   python -m pip install -e .[docs]
+
+```
+
+From the root of the project.
+Some of the examples rely on `rpy2` to execute R code from the notebooks.
+It's not included in the setup requires since it's known to be difficult to
+install.
+
+To generate the HTML docs, run ``make html`` from the ``docs`` directory.
+This executes a few distinct builds
+
+1. datasets
+2. notebooks
+3. sphinx
+
+# Notebook Builds
+
+We're using `nbconvert` to execute the notebooks, and then convert them
+to HTML. The conversion is handled by `statsmodels/tools/nbgenerate.py`.
+The default python kernel (embedded in the notebook) is `python3`.
+You need at least `nbconvert==4.2.0` to specify a non-default kernel,
+which can be passed in the Makefile.

statsmodels/source/docs/make.bat

@@ -0,0 +1,58 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+set TOOLSPATH=../tools
+set DATASETBUILD=dataset_rst.py
+set NOTEBOOKBUILD=nbgenerate.py
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "html" (
+    echo mkdir %BUILDDIR%\html\_static
+    mkdir %BUILDDIR%\html\_static
+	echo python %TOOLSPATH%/%NOTEBOOKBUILD% --parallel --report-errors --skip-existing
+	rem Black list notebooks from doc build here
+    python %TOOLSPATH%/%NOTEBOOKBUILD% --parallel --report-errors --skip-existing --execution-blacklist statespace_custom_models
+    echo python %TOOLSPATH%/%DATASETBUILD%
+    python %TOOLSPATH%/%DATASETBUILD%
+)
+
+echo %SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+if "%1" == "html" (
+    echo xcopy /s /y source\examples\notebooks\generated\*.html %BUILDDIR%\html\examples\notebooks\generated\*.html
+    xcopy /s /y source\examples\notebooks\generated\*.html %BUILDDIR%\html\examples\notebooks\generated\*.html
+    if NOT EXIST %BUILDDIR%/html/examples/notebooks/generated mkdir %BUILDDIR%\html\examples\notebooks\generated
+)
+
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

statsmodels/source/docs/source/_static/facebox.css

@@ -0,0 +1,80 @@
+#facebox {
+  position: absolute;
+  top: 0;
+  left: 0;
+  z-index: 100;
+  text-align: left;
+}
+
+
+#facebox .popup{
+  position:relative;
+  border:3px solid rgba(0,0,0,0);
+  -webkit-border-radius:5px;
+  -moz-border-radius:5px;
+  border-radius:5px;
+  -webkit-box-shadow:0 0 18px rgba(0,0,0,0.4);
+  -moz-box-shadow:0 0 18px rgba(0,0,0,0.4);
+  box-shadow:0 0 18px rgba(0,0,0,0.4);
+}
+
+#facebox .content {
+  display:table;
+  width: 370px;
+  padding: 10px;
+  background: #fff;
+  -webkit-border-radius:4px;
+  -moz-border-radius:4px;
+  border-radius:4px;
+}
+
+#facebox .content > p:first-child{
+  margin-top:0;
+}
+#facebox .content > p:last-child{
+  margin-bottom:0;
+}
+
+#facebox .close{
+  position:absolute;
+  top:5px;
+  right:5px;
+  padding:2px;
+  background:#fff;
+}
+#facebox .close img{
+  opacity:0.3;
+}
+#facebox .close:hover img{
+  opacity:1.0;
+}
+
+#facebox .loading {
+  text-align: center;
+}
+
+#facebox .image {
+  text-align: center;
+}
+
+#facebox img {
+  border: 0;
+  margin: 0;
+}
+
+#facebox_overlay {
+  position: fixed;
+  top: 0px;
+  left: 0px;
+  height:100%;
+  width:100%;
+}
+
+.facebox_hide {
+  z-index:-100;
+}
+
+.facebox_overlayBG {
+  background-color: #000;
+  z-index: 99;
+}