update project

.pre-commit-config.yaml

@@ -0,0 +1,34 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      # - id: check-added-large-files
+  - repo: https://github.com/psf/black
+    rev: 23.3.0
+    hooks:
+      # - id: black
+      - id: black-jupyter
+  - repo: https://github.com/pycqa/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        name: isort (python)
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.3.1
+    hooks:
+      - id: pyupgrade
+        args: [--py311-plus]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.7.0
+    hooks:
+      - id: nbqa-isort
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: [--py311-plus]
+default_language_version:
+  python: python3.11

README.md

@@ -1,8 +1,8 @@
 ---
-title: Sklearn Ocsvm Vs Sgdocsvm
-emoji: 🔥
-colorFrom: indigo
-colorTo: pink
+title: Sklearn Lm L1 L2 Sparsity
+emoji: 📉
+colorFrom: gray
+colorTo: red
 sdk: gradio
 sdk_version: 3.24.1
 app_file: app.py

app.py

@@ -0,0 +1,260 @@
+import gradio as gr
+import numpy as np
+import matplotlib.pyplot as plt
+import matplotlib
+from sklearn.svm import OneClassSVM
+from sklearn.linear_model import SGDOneClassSVM
+from sklearn.kernel_approximation import Nystroem
+from sklearn.pipeline import make_pipeline
+
+font = {"weight": "normal", "size": 15}
+
+matplotlib.rc("font", **font)
+
+random_state = 42
+rng = np.random.default_rng(random_state)
+
+# Generate train data
+X = 0.3 * rng.random((500, 2))
+X_train = np.r_[X + 2, X - 2]
+# Generate some regular novel observations
+X = 0.3 * rng.random((20, 2))
+X_test = np.r_[X + 2, X - 2]
+# Generate some abnormal novel observations
+X_outliers = rng.uniform(low=-4, high=4, size=(20, 2))
+
+xx, yy = np.meshgrid(np.linspace(-4.5, 4.5, 50), np.linspace(-4.5, 4.5, 50))
+
+# OCSVM hyperparameters
+# nu = 0.05
+# gamma = 2.0
+
+md_description = """
+# A 1D regression with decision tree.
+
+The [decision trees](https://scikit-learn.org/stable/modules/tree.html#tree) is used to fit a sine curve with addition noisy observation. As a result, it learns local linear regressions approximating the sine curve.
+
+We can see that if the maximum depth of the tree (controlled by the max_depth parameter) is set too high, the decision trees learn too fine details of the training data and learn from the noise, i.e. they overfit.
+"""
+
+
+def make_regression(nu, gamma):
+    clf = OneClassSVM(gamma=gamma, kernel="rbf", nu=nu)
+    clf.fit(X_train)
+    y_pred_train = clf.predict(X_train)
+    y_pred_test = clf.predict(X_test)
+    y_pred_outliers = clf.predict(X_outliers)
+    n_error_train = y_pred_train[y_pred_train == -1].size
+    n_error_test = y_pred_test[y_pred_test == -1].size
+    n_error_outliers = y_pred_outliers[y_pred_outliers == 1].size
+
+    Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
+    Z = Z.reshape(xx.shape)
+
+
+    # Fit the One-Class SVM using a kernel approximation and SGD
+    transform = Nystroem(gamma=gamma, random_state=random_state)
+    clf_sgd = SGDOneClassSVM(
+        nu=nu, shuffle=True, fit_intercept=True, random_state=random_state, tol=1e-4
+    )
+    pipe_sgd = make_pipeline(transform, clf_sgd)
+    pipe_sgd.fit(X_train)
+    y_pred_train_sgd = pipe_sgd.predict(X_train)
+    y_pred_test_sgd = pipe_sgd.predict(X_test)
+    y_pred_outliers_sgd = pipe_sgd.predict(X_outliers)
+    n_error_train_sgd = y_pred_train_sgd[y_pred_train_sgd == -1].size
+    n_error_test_sgd = y_pred_test_sgd[y_pred_test_sgd == -1].size
+    n_error_outliers_sgd = y_pred_outliers_sgd[y_pred_outliers_sgd == 1].size
+
+    Z_sgd = pipe_sgd.decision_function(np.c_[xx.ravel(), yy.ravel()])
+    Z_sgd = Z_sgd.reshape(xx.shape)
+    
+    def make_fig_1():
+        # plot the level sets of the decision function
+        fig = plt.figure(figsize=(9, 6))
+        # fig, ax = plt.subplots(1, 1, figsize=(9,6))
+        ax = fig.add_subplot(111)
+        
+        ax.set_title("One Class SVM")
+        ax.contourf(xx, yy, Z, levels=np.linspace(Z.min(), 0, 7), cmap=plt.cm.PuBu)
+        a = ax.contour(xx, yy, Z, levels=[0], linewidths=2, colors="darkred")
+        ax.contourf(xx, yy, Z, levels=[0, Z.max()], colors="palevioletred")
+
+        s = 20
+        b1 = ax.scatter(X_train[:, 0], X_train[:, 1], c="white", s=s, edgecolors="k")
+        b2 = ax.scatter(X_test[:, 0], X_test[:, 1], c="blueviolet", s=s, edgecolors="k")
+        c = ax.scatter(X_outliers[:, 0], X_outliers[:, 1], c="gold", s=s, edgecolors="k")
+        ax.axis("tight")
+        ax.set_xlim((-4.5, 4.5))
+        ax.set_ylim((-4.5, 4.5))
+        ax.legend(
+            [a.collections[0], b1, b2, c],
+            [
+                "learned frontier",
+                "training observations",
+                "new regular observations",
+                "new abnormal observations",
+            ],
+            loc="upper left",
+        )
+        ax.set_xlabel(
+            "error train: %d/%d; errors novel regular: %d/%d; errors novel abnormal: %d/%d"
+            % (
+                n_error_train,
+                X_train.shape[0],
+                n_error_test,
+                X_test.shape[0],
+                n_error_outliers,
+                X_outliers.shape[0],
+            )
+        )
+        
+        return fig
+
+    def make_fig_2():
+        fig = plt.figure(figsize=(9, 6))
+        ax = fig.add_subplot(111)
+        # fig, ax = plt.subplots(1, 1)
+        
+        ax.set_title("Online One-Class SVM2")
+        ax.contourf(xx, yy, Z_sgd, levels=np.linspace(Z_sgd.min(), 0, 7), cmap=plt.cm.PuBu)
+        a = plt.contour(xx, yy, Z_sgd, levels=[0], linewidths=2, colors="darkred")
+        ax.contourf(xx, yy, Z_sgd, levels=[0, Z_sgd.max()], colors="palevioletred")
+
+        s = 20
+        b1 = ax.scatter(X_train[:, 0], X_train[:, 1], c="white", s=s, edgecolors="k")
+        b2 = ax.scatter(X_test[:, 0], X_test[:, 1], c="blueviolet", s=s, edgecolors="k")
+        c = ax.scatter(X_outliers[:, 0], X_outliers[:, 1], c="gold", s=s, edgecolors="k")
+        ax.axis("tight")
+        ax.set_xlim((-4.5, 4.5))
+        ax.set_ylim((-4.5, 4.5))
+        ax.legend(
+            [a.collections[0], b1, b2, c],
+            [
+                "learned frontier",
+                "training observations",
+                "new regular observations",
+                "new abnormal observations",
+            ],
+            loc="upper left",
+        )
+        ax.set_xlabel(
+            "error train: %d/%d; errors novel regular: %d/%d; errors novel abnormal: %d/%d"
+            % (
+                n_error_train_sgd,
+                X_train.shape[0],
+                n_error_test_sgd,
+                X_test.shape[0],
+                n_error_outliers_sgd,
+                X_outliers.shape[0],
+            )
+        )
+        
+        return fig
+        
+        
+        
+
+    return make_fig_2(), make_fig_2()
+
+# def make_figure():
+#     fig = plt.figure(figsize=(9, 6))
+
+#     plt.title("One Class SVM")
+#     plt.contourf(xx, yy, Z, levels=np.linspace(Z.min(), 0, 7), cmap=plt.cm.PuBu)
+#     a = plt.contour(xx, yy, Z, levels=[0], linewidths=2, colors="darkred")
+#     plt.contourf(xx, yy, Z, levels=[0, Z.max()], colors="palevioletred")
+
+#     s = 20
+#     b1 = plt.scatter(X_train[:, 0], X_train[:, 1], c="white", s=s, edgecolors="k")
+#     b2 = plt.scatter(X_test[:, 0], X_test[:, 1], c="blueviolet", s=s, edgecolors="k")
+#     c = plt.scatter(X_outliers[:, 0], X_outliers[:, 1], c="gold", s=s, edgecolors="k")
+#     plt.axis("tight")
+#     plt.xlim((-4.5, 4.5))
+#     plt.ylim((-4.5, 4.5))
+#     plt.legend(
+#         [a.collections[0], b1, b2, c],
+#         [
+#             "learned frontier",
+#             "training observations",
+#             "new regular observations",
+#             "new abnormal observations",
+#         ],
+#         loc="upper left",
+#     )
+#     plt.xlabel(
+#         "error train: %d/%d; errors novel regular: %d/%d; errors novel abnormal: %d/%d"
+#         % (
+#             n_error_train,
+#             X_train.shape[0],
+#             n_error_test,
+#             X_test.shape[0],
+#             n_error_outliers,
+#             X_outliers.shape[0],
+#         )
+#     )
+#     plt.show()
+    
+
+def make_example(model_1_depth, model_2_depth):
+    return f"""
+    With the following code you can reproduce this example with the current values of the sliders and the same data in a notebook:
+
+    ```python
+    import numpy as np
+    import plotly.graph_objects as go
+    from sklearn.tree import DecisionTreeRegressor
+
+    rng = np.random.default_rng(0)
+
+    X = np.sort(5 * rng.random((80, 1)), axis=0)
+    y = np.sin(X).ravel()
+    y[::5] += 3 * (0.5 - rng.random(16))
+
+    regr_1 = DecisionTreeRegressor(max_depth={model_1_depth}, random_state=0)
+    regr_2 = DecisionTreeRegressor(max_depth={model_2_depth}, random_state=0)
+    regr_1.fit(X, y)
+    regr_2.fit(X, y)
+
+    # Predict
+    X_test = np.arange(0.0, 5.0, 0.01)[:, np.newaxis]
+    y_1 = regr_1.predict(X_test)
+    y_2 = regr_2.predict(X_test)
+
+
+    fig = go.Figure()
+    fig.add_trace(go.Scatter(x=X[:,0], y=y, mode='markers', name='data'))
+    fig.add_trace(go.Scatter(x=X_test[:,0], y=y_1, mode='lines', name=f"max_depth={model_1_depth}"))
+    fig.add_trace(go.Scatter(x=X_test[:,0], y=y_2, mode='lines', name=f"max_depth={model_2_depth}"))
+
+    fig.update_layout(title='Decision Tree Regression')
+    fig.update_xaxes(title_text='data')
+    fig.update_yaxes(title_text='target')
+    fig.show()
+    ```
+    """
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        gr.Markdown(md_description)
+    with gr.Row():
+        # with gr.Column():
+        slider_nu = gr.Slider(minimum=0.01, maximum=1, label='Nu', step=0.025, value=0.05)
+        slider_gamma = gr.Slider(minimum=0.1, maximum=3, label='Gamma', step=0.1, value=2.0)
+        button = gr.Button("Generate")
+    with gr.Row():
+        plot1 = gr.Plot(label='Output')
+    with gr.Row():
+        plot2 = gr.Plot(label='Output')
+
+    with gr.Row():
+        example = gr.Markdown(make_example(slider_nu.value, slider_gamma.value))
+        slider_nu.change(fn=make_regression, 
+            inputs=[slider_nu, slider_gamma], 
+            outputs=[plot1, plot2])
+        slider_gamma.change(fn=make_regression, 
+            inputs=[slider_nu, slider_gamma], 
+            outputs=[plot1, plot2])
+        button.click(make_regression, inputs=[slider_nu, slider_gamma], outputs=[plot1, plot2])
+
+demo.launch()

poetry.toml

@@ -0,0 +1,2 @@
+[virtualenvs]
+in-project = true

pyproject.toml

@@ -0,0 +1,53 @@
+[tool.poetry]
+name = "sklearn-decision-tree-regression"
+version = "0.1.0"
+description = "Hugging Face Scikit Learn Demos"
+authors = ["Niels van Galen Last <nvangalenlast@gmail.com>"]
+license = "MIT"
+readme = "README.md"
+# packages = [{ include = "huggingface_sklearn" }]
+
+[tool.poetry.dependencies]
+python = ">=3.8.9,<3.12"
+numpy = "^1.24.2"
+scikit-learn = "^1.2.2"
+matplotlib = "^3.7.1"
+plotly = "^5.14.0"
+gradio = "^3.24.1"
+
+
+[tool.poetry.group.dev.dependencies]
+black = { extras = ["jupyter"], version = "^23.3.0" }
+isort = "^5.12.0"
+pre-commit = "^3.2.1"
+pylint = "^2.17.1"
+pytest = "^7.2.2"
+jupyterlab = "^3.6.3"
+jupyterlab-widgets = "^3.0.7"
+ipywidgets = "^8.0.6"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.black]
+line-length = 100
+target_version = ['py311']
+include = '\.py$'
+
+[tool.isort]
+profile = "black"
+# force_single_line = "false"
+force_sort_within_sections = "true"
+line_length = 100
+
+[tool.pylint]
+[tool.pylint.messages_control]
+#line-too-long='off'
+disable = """
+    invalid-name,
+    logging-fstring-interpolation,
+    missing-class-docstring,
+    missing-function-docstring,
+    missing-module-docstring,
+    """

requirements.txt

@@ -0,0 +1,74 @@
+aiofiles==22.1.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+aiohttp==3.8.4 ; python_full_version >= "3.8.9" and python_version < "3.12"
+aiosignal==1.3.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+altair==4.2.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+anyio==3.6.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+async-timeout==4.0.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+attrs==22.2.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+certifi==2022.12.7 ; python_full_version >= "3.8.9" and python_version < "3.12"
+charset-normalizer==3.1.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+click==8.1.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+colorama==0.4.6 ; python_full_version >= "3.8.9" and python_version < "3.12" and platform_system == "Windows"
+contourpy==1.0.7 ; python_full_version >= "3.8.9" and python_version < "3.12"
+cycler==0.11.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+entrypoints==0.4 ; python_full_version >= "3.8.9" and python_version < "3.12"
+fastapi==0.95.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+ffmpy==0.3.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+filelock==3.10.7 ; python_full_version >= "3.8.9" and python_version < "3.12"
+fonttools==4.39.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+frozenlist==1.3.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+fsspec==2023.3.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+gradio-client==0.0.5 ; python_full_version >= "3.8.9" and python_version < "3.12"
+gradio==3.24.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+h11==0.14.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+httpcore==0.16.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+httpx==0.23.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+huggingface-hub==0.13.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+idna==3.4 ; python_full_version >= "3.8.9" and python_version < "3.12"
+importlib-resources==5.12.0 ; python_full_version >= "3.8.9" and python_version < "3.10"
+jinja2==3.1.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+joblib==1.2.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+jsonschema==4.17.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+kiwisolver==1.4.4 ; python_full_version >= "3.8.9" and python_version < "3.12"
+linkify-it-py==2.0.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+markdown-it-py==2.2.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+markdown-it-py[linkify]==2.2.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+markupsafe==2.1.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+matplotlib==3.7.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+mdit-py-plugins==0.3.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+mdurl==0.1.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+multidict==6.0.4 ; python_full_version >= "3.8.9" and python_version < "3.12"
+numpy==1.24.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+orjson==3.8.9 ; python_full_version >= "3.8.9" and python_version < "3.12"
+packaging==23.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pandas==1.5.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pillow==9.5.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pkgutil-resolve-name==1.3.10 ; python_full_version >= "3.8.9" and python_version < "3.9"
+plotly==5.14.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pydantic==1.10.7 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pydub==0.25.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pyparsing==3.0.9 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pyrsistent==0.19.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+python-dateutil==2.8.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+python-multipart==0.0.6 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pytz==2023.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+pyyaml==6.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+requests==2.28.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+rfc3986[idna2008]==1.5.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+scikit-learn==1.2.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+scipy==1.9.3 ; python_full_version >= "3.8.9" and python_version < "3.12"
+semantic-version==2.10.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+six==1.16.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+sniffio==1.3.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+starlette==0.26.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+tenacity==8.2.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+threadpoolctl==3.1.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+toolz==0.12.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+tqdm==4.65.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+typing-extensions==4.5.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+uc-micro-py==1.0.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+urllib3==1.26.15 ; python_full_version >= "3.8.9" and python_version < "3.12"
+uvicorn==0.21.1 ; python_full_version >= "3.8.9" and python_version < "3.12"
+websockets==11.0 ; python_full_version >= "3.8.9" and python_version < "3.12"
+yarl==1.8.2 ; python_full_version >= "3.8.9" and python_version < "3.12"
+zipp==3.15.0 ; python_full_version >= "3.8.9" and python_version < "3.10"