sync with remote

app.py

@@ -0,0 +1,85 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.metrics import mean_squared_error, r2_score
+import pickle
+from huggingface_hub import HfApi, HfFolder
+
+# Load the dataset
+df = pd.read_csv('advertising.csv')
+
+# Display the dataset
+st.write("## Advertising Dataset")
+st.write(df)
+
+# Scatter plots
+fig, axs = plt.subplots(1, 3, figsize=(15, 5))
+axs[0].scatter(df['TV'], df['Sales'])
+axs[0].set_xlabel('TV')
+axs[0].set_ylabel('Sales')
+axs[0].set_title('TV vs Sales')
+
+axs[1].scatter(df['Radio'], df['Sales'])
+axs[1].set_xlabel('Radio')
+axs[1].set_ylabel('Sales')
+axs[1].set_title('Radio vs Sales')
+
+axs[2].scatter(df['Newspaper'], df['Sales'])
+axs[2].set_xlabel('Newspaper')
+axs[2].set_ylabel('Sales')
+axs[2].set_title('Newspaper vs Sales')
+
+st.pyplot(fig)
+
+# Split the data into training and testing sets
+X = df[['TV', 'Radio', 'Newspaper']]
+y = df['Sales']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train the decision tree regressor
+regressor = DecisionTreeRegressor(random_state=42)
+regressor.fit(X_train, y_train)
+
+# Predict on the test set
+y_pred = regressor.predict(X_test)
+
+# Calculate performance metrics
+mse = mean_squared_error(y_test, y_pred)
+r2 = r2_score(y_test, y_pred)
+
+# Display performance metrics
+st.write("## Model Performance")
+st.write(f"Mean Squared Error: {mse}")
+st.write(f"R-squared: {r2}")
+
+# Save the trained model as a pickle file
+model_path = 'decision_tree_regressor.pkl'
+with open(model_path, 'wb') as f:
+    pickle.dump(regressor, f)
+
+# About this app section
+with st.expander("About This App"):
+    st.write("""
+    This app reads the advertising dataset and trains a decision tree regressor to predict sales based on TV, Radio, and Newspaper advertising budgets.
+    The dataset is sourced from Kaggle and contains information on advertising budgets and sales for a product.
+    The app displays scatter plots of TV vs Sales, Radio vs Sales, and Newspaper vs Sales.
+    After training the model, the app displays the performance metrics of the model.
+    The trained model is saved as a pickle file for future use.
+    """)
+
+# Code to upload the trained model to Hugging Face using huggingface_hub
+hf_token = os.getenv("HF_TOKEN")
+repo_id = "wvsu-dti-aidev-team/advertising_knn_regressor_model"
+
+api = HfApi()
+api.upload_file(
+    path_or_fileobj=model_path,
+    path_in_repo=model_path,
+    repo_id=repo_id,
+    repo_type="model",
+    token=hf_token
+)
+
+st.write("Model uploaded successfully!")

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+matplotlib
+scikit-learn
+requests
+huggingface_hub