Upload folder using huggingface_hub

Dockerfile

@@ -1,21 +1,16 @@
-FROM python:3.9-slim
-
-WORKDIR /app
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
-
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working directory
+COPY . .
+
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:sales_predictor_api"]

XGBoost_best_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37682de00f58050b36c832de82200b17a7703b6a95573e6f20a5beee36aa6b0b
+size 2510935

app.py

@@ -0,0 +1,73 @@
+# Import necessary libraries
+import numpy as np
+import joblib  # For loading the serialized model
+import pandas as pd  # For data manipulation
+from flask import Flask, request, jsonify  # For creating the Flask API
+
+import pandas as pd
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.preprocessing import PowerTransformer, OrdinalEncoder
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+import sys
+
+from custom_transformers import SkewnessCapper
+
+print ( "Overriding Skewness Capper")
+sys.modules['__main__'].SkewnessCapper = SkewnessCapper
+print ( "Overriding Skewness Capper success")
+
+print( " Trying to load XGBoost model using joblib")
+model = joblib.load("XGBoost_best_model.joblib")
+
+print("Model loaded successfully!")
+
+# Initialize the Flask application
+sales_predictor_api = Flask("SuperKart Sales Prediction")
+
+# Define a route for the home page (GET request)
+@sales_predictor_api.get('/')
+def home():
+    """
+    This function handles GET requests to the root URL ('/') of the API.
+    It returns a simple welcome message.
+    """
+    return "Welcome to the SuperKart Sales Prediction API!"
+
+# Define an endpoint for single property prediction (POST request)
+@sales_predictor_api.post('/v1/sales')
+def predict_sales():
+    """
+    This function handles POST requests to the '/v1/sales' endpoint.
+    It expects a JSON payload containing property details and returns
+    the predicted rental price as a JSON response.
+    """
+    # Get the JSON data from the request body
+    property_data = request.get_json()
+
+    # Extract relevant features from the JSON data
+    sample = {
+        'Product_Weight': property_data['Product_Weight'],
+        'Product_Allocated_Area': property_data['Product_Allocated_Area'],
+        'Product_MRP': property_data['Product_MRP'],
+        'Product_Sugar_Content': property_data['Product_Sugar_Content'],
+        'Product_Type': property_data['Product_Type'],
+        'Store_Establishment_Year': property_data['Store_Establishment_Year'],
+        'Store_Size': property_data['Store_Size'],
+        'Store_Location_City_Type': property_data['Store_Location_City_Type'],
+        'Store_Type': property_data['Store_Type']
+    }
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (get log_price)
+    predicted_sales = model.predict(input_data)[0]
+
+    # Return the actual price
+    return jsonify({'Predicted Sales = ': predicted_sales})
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == '__main__':
+    sales_predictor_api.run(debug=True)

custom_transformers.py

@@ -0,0 +1,73 @@
+import pandas as pd
+import numpy as np
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.preprocessing import PowerTransformer, OrdinalEncoder
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+
+# ===== Custom Transformer for Skewness and Capping =====
+class SkewnessCapper(BaseEstimator, TransformerMixin):
+    def __init__(self, skew_threshold=0.5, cap_factor=3.0):
+        self.skew_threshold = skew_threshold
+        self.cap_factor = cap_factor
+        self.skewed_features_ = None
+        self.feature_caps_ = {}
+
+    def fit(self, X, y=None):
+        X = pd.DataFrame(X)
+        skewness = X.apply(lambda col: col.skew(skipna=True))
+        self.skewed_features_ = skewness[abs(skewness) > self.skew_threshold].index.tolist()
+        
+        # Store caps for each feature
+        for col in X.columns:
+            mean, std = X[col].mean(), X[col].std()
+            self.feature_caps_[col] = (mean - self.cap_factor * std, mean + self.cap_factor * std)
+        return self
+
+    def transform(self, X):
+        X = pd.DataFrame(X).copy()
+        # Cap values
+        for col, (lower, upper) in self.feature_caps_.items():
+            X[col] = np.clip(X[col], lower, upper)
+        # Transform skewed columns
+        for col in self.skewed_features_:
+            X[col] = np.log1p(X[col] - X[col].min() + 1)
+        return X
+
+# ===== Example Data =====
+df = pd.DataFrame({
+    'num1': [1, 2, 3, 100, 5],
+    'num2': [10, 15, 14, 13, 1000],
+    'cat1': ['A', 'B', 'A', 'C', 'B'],
+    'cat2': ['X', 'X', 'Y', 'Z', 'Y']
+})
+
+# Separate numeric and categorical columns
+num_features = df.select_dtypes(include=[np.number]).columns.tolist()
+cat_features = df.select_dtypes(exclude=[np.number]).columns.tolist()
+
+# ===== Pipelines for Numeric & Categorical =====
+numeric_pipeline = Pipeline(steps=[
+    ('skew_cap', SkewnessCapper())
+])
+
+categorical_pipeline = Pipeline(steps=[
+    ('encode', OrdinalEncoder(handle_unknown='use_encoded_value', unknown_value=-1))
+])
+
+# ===== Combine into ColumnTransformer =====
+preprocessor = ColumnTransformer(
+    transformers=[
+        ('num', numeric_pipeline, num_features),
+        ('cat', categorical_pipeline, cat_features)
+    ]
+)
+
+# ===== Full Pipeline =====
+full_pipeline = Pipeline(steps=[
+    ('preprocessor', preprocessor)
+])
+
+# ===== Transform the Data =====
+df_transformed = full_pipeline.fit_transform(df)
+print(pd.DataFrame(df_transformed))

requirements.txt

@@ -1,3 +1,11 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests==2.28.1
+uvicorn[standard]
+streamlit==1.43.2