ddd

Dockerfile

@@ -0,0 +1,26 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim-buster
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+# This includes main.py, requirements.txt, and the models/ directory
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Create a directory for your models if it doesn't exist
+# (though it should be copied from local)
+RUN mkdir -p models
+
+# Expose the port FastAPI will run on. Hugging Face Spaces often expects 
+# port 7860 for web apps.
+EXPOSE 7860
+
+# Command to run the Uvicorn server
+# The --host 0.0.0.0 makes the server accessible from outside the 
+# container
+# The --port 7860 matches the EXPOSE instruction
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,11 +1,111 @@
 ---
+<<<<<<< HEAD
 title: My Fastapi Endpoint
-emoji: 📈
+emoji: 🏃
 colorFrom: gray
-colorTo: blue
+colorTo: purple
 sdk: docker
 pinned: false
 license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+=======
+title: My FastAPI App
+emoji: 🌍
+colorFrom: red
+colorTo: red
+sdk: docker
+pinned: false
+license: mit
+short_description: This is a taxi predictor!
+---
+
+# FastAPI Taxi Trip Duration Prediction API
+
+This project provides a FastAPI-based REST API for predicting taxi trip durations in different cities using pre-trained Ridge regression models.
+
+## How to Use
+
+### 1. Running the API
+
+- **Locally:**  
+  Start the server with:
+  ```sh
+  uvicorn main:app --host 0.0.0.0 --port 7860
+  ```
+- **On Hugging Face Spaces:**  
+  The API will be available at  
+  `https://<your-username>-<your-space-name>.hf.space/predict`
+
+### 2. Sending a Prediction Request
+
+You can send a POST request to the `/predict` endpoint using any HTTP client (such as `curl`, Postman, or Python's `requests` library).
+
+#### Example Python snippet
+
+```python
+import requests
+
+API_URL = "https://<your-username>-<your-space-name>.hf.space/predict"
+# If your Space is private, uncomment and set your token:
+# HF_TOKEN = "hf_xxx..."
+# headers = {"Authorization": f"Bearer {HF_TOKEN}"}
+headers = {}
+
+data = {
+    "vendor_id": "Bogotá UberX",
+    "dist_meters": 18.976,
+    "wait_sec": 1640,
+    "geodetic_dist": 15.439039,
+    "mean_velocity": 17.172851,
+    "is_rush_hour": False,
+    "model_name": "bog"
+}
+
+response = requests.post(API_URL, json=data, headers=headers)
+print(response.json())
+```
+
+### 3. Datapoint Format
+
+The API expects a JSON object with the following fields:
+
+| Field         | Type   | Example Value  | Description                                      |
+| ------------- | ------ | -------------- | ------------------------------------------------ |
+| vendor_id     | string | "Bogotá UberX" | The taxi vendor or service name                  |
+| dist_meters   | float  | 18.976         | Distance of the trip in meters                   |
+| wait_sec      | float  | 1640           | Waiting time in seconds                          |
+| geodetic_dist | float  | 15.439039      | Geodetic (straight-line) distance                |
+| mean_velocity | float  | 17.172851      | Mean velocity during the trip                    |
+| is_rush_hour  | bool   | false          | Whether the trip occurred during rush hour       |
+| model_name    | string | "bog"          | Which model to use: `"bog"`, `"mex"`, or `"uio"` |
+
+**Example JSON datapoint:**
+
+```json
+{
+  "vendor_id": "Bogotá UberX",
+  "dist_meters": 18.976,
+  "wait_sec": 1640,
+  "geodetic_dist": 15.439039,
+  "mean_velocity": 17.172851,
+  "is_rush_hour": false,
+  "model_name": "bog"
+}
+```
+
+### 4. Response Format
+
+The API will return a JSON response like:
+
+```json
+{
+  "trip_duration": 123.45,
+  "model_used": "bog",
+  "message": "Inference successful using BOG model."
+}
+```
+
+---
+>>>>>>> 531d625 (Commiiitt!)

app.py

@@ -0,0 +1,82 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import uvicorn
+import os
+import joblib
+import pandas as pd
+
+# --- 0. Initialize FastAPI app ---
+app = FastAPI()
+
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the Taxi Fare Prediction API. Use POST /predict to get predictions."}
+
+# --- 1. Define Input and Output Data Models ---
+class InferenceInput(BaseModel):
+    vendor_id: str
+    dist_meters: float
+    wait_sec: float
+    geodetic_dist: float
+    mean_velocity: float
+    is_rush_hour: bool
+    model_name: str  # "bog", "mex", or "uio"
+
+class InferenceOutput(BaseModel):
+    trip_duration: float
+    model_used: str
+    message: str
+
+# --- 2. Define ML Model Manager Class ---
+class MLModels:
+    def __init__(self):
+        model_dir = "models"
+        self.bog_pipeline = self.load_pipeline(os.path.join(model_dir, "bog_ridge_pipeline.pkl"))
+        self.mex_pipeline = self.load_pipeline(os.path.join(model_dir, "mex_ridge_pipeline.pkl"))
+        self.uio_pipeline = self.load_pipeline(os.path.join(model_dir, "uio_ridge_pipeline.pkl"))
+
+    def load_pipeline(self, path):
+        if os.path.exists(path):
+            return joblib.load(path)
+        else:
+            raise FileNotFoundError(f"Model file not found: {path}")
+
+    def predict_one(self, features: dict, model_name: str):
+        model_map = {
+            "bog": self.bog_pipeline,
+            "mex": self.mex_pipeline,
+            "uio": self.uio_pipeline
+        }
+        pipeline = model_map.get(model_name.lower())
+        if not pipeline:
+            raise ValueError(f"Model '{model_name}' not found. Choose from 'bog', 'mex', or 'uio'.")
+        X_df = pd.DataFrame([features])
+        pred = pipeline.predict(X_df)[0]
+        return float(pred)
+
+# --- 3. Initialize ML Model Manager ---
+ml_models = MLModels()
+
+# --- 4. Define Inference Endpoint ---
+@app.post("/predict", response_model=InferenceOutput)
+async def predict_inference(data: InferenceInput):
+    try:
+        features = data.dict()
+        model_name = features.pop("model_name")
+        trip_duration = ml_models.predict_one(features, model_name)
+        return InferenceOutput(
+            trip_duration=trip_duration,
+            model_used=model_name,
+            message=f"Inference successful using {model_name.upper()} model."
+        )
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Inference failed: {str(e)}")
+
+# --- 5. Run the Application (for local development) ---
+if __name__ == "__main__":
+    port_number = 7860  # Use 7860 to match Gradio UI port if needed
+    host = os.getenv("FASTAPI_HOST", "127.0.0.1")
+    port = int(os.getenv("FASTAPI_PORT", port_number))
+    print(f"FastAPI application starting on http://{host}:{port}")
+    print(f"Access the API documentation (Swagger UI) at http://{host}:{port}/docs")
+    uvicorn.run(app, host=host, port=port)

models/bog_ridge_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5708a4e33b6c3f4b1e9ca38abc12ed241ae558bc95b66f75011b5f22778ec33
+size 3473

models/mex_ridge_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7779475db1d7865b5df33131aa66bc82b09c7031fe48f82821f1ca56c97e0833
+size 3553

models/uio_ridge_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c71ea9c30a02dccc12dadbfcf19d8b67fd1eb2e88c8bcd9da035b1825145fa
+size 3449

requirements.txt

@@ -0,0 +1,32 @@
+annotated-types==0.7.0
+anyio==4.9.0
+certifi==2025.4.26
+charset-normalizer==3.4.2
+click==8.1.8
+exceptiongroup==1.3.0
+fastapi==0.115.12
+h11==0.16.0
+idna==3.10
+joblib==1.5.1
+lightgbm==4.6.0
+numpy==2.0.2
+pandas==2.3.0
+pip==25.1
+pydantic==2.11.5
+pydantic_core==2.33.2
+python-dateutil==2.9.0.post0
+pytz==2025.2
+requests==2.32.4
+scikit-learn==1.6.1
+scipy==1.13.1
+setuptools==78.1.1
+six==1.17.0
+sniffio==1.3.1
+starlette==0.46.2
+threadpoolctl==3.6.0
+typing_extensions==4.14.0
+typing-inspection==0.4.1
+tzdata==2025.2
+urllib3==2.4.0
+uvicorn==0.34.3
+wheel==0.45.1