import streamlit as st import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.datasets import fetch_california_housing from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error, r2_score # Titre de l'application st.title('California Housing Prices Prediction') # Charger les données california = fetch_california_housing() df = pd.DataFrame(california.data, columns=california.feature_names) df['MedHouseVal'] = california.target # Valeur médiane des maisons # Afficher les données st.write("## Data Overview") st.write(df.head()) # Visualiser les relations st.write("## Scatter Plot") fig, ax = plt.subplots() ax.scatter(df['AveRooms'], df['MedHouseVal']) ax.set_xlabel('Average number of rooms per dwelling') ax.set_ylabel('Median house value') st.pyplot(fig) # Sélectionner le prédicteur X = df[['AveRooms']] y = df['MedHouseVal'] # Diviser les données en ensembles d'entraînement et de test X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) # Créer et entraîner le modèle de régression linéaire lr_model = LinearRegression() lr_model.fit(X_train, y_train) y_pred = lr_model.predict(X_test) # Évaluer la performance du modèle rmse = np.sqrt(mean_squared_error(y_test, y_pred)) r2 = r2_score(y_test, y_pred) st.write(f'## Linear Regression Model Performance') st.write(f'RMSE: {rmse:.2f}') st.write(f'R-squared: {r2:.2f}') # Visualiser la ligne de régression st.write("## Regression Line") fig, ax = plt.subplots() ax.scatter(X_test['AveRooms'], y_test, color='blue') ax.plot(X_test['AveRooms'], y_pred, color='red') ax.set_xlabel('Average number of rooms per dwelling') ax.set_ylabel('Median house value') st.pyplot(fig) # Multirégression linéaire X = df.drop('MedHouseVal', axis=1) y = df['MedHouseVal'] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42) mlr_model = LinearRegression() mlr_model.fit(X_train, y_train) y_pred = mlr_model.predict(X_test) rmse_ml = np.sqrt(mean_squared_error(y_test, y_pred)) r2_ml = r2_score(y_test, y_pred) st.write(f'## Multilinear Regression Model Performance') st.write(f'RMSE: {rmse_ml:.2f}') st.write(f'R-squared: {r2_ml:.2f}') st.write("## Multilinear Regression Predictions") fig, ax = plt.subplots() ax.scatter(y_test, y_pred) ax.set_xlabel('Actual Median House Value') ax.set_ylabel('Predicted Median House Value') ax.set_title('Multilinear Regression Model Predictions') st.pyplot(fig)

app.py

@@ -1 +1,81 @@
 !pip install streamlit transformers datasets scikit-learn matplotlib
+import streamlit as st
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.datasets import fetch_california_housing
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error, r2_score
+
+# Titre de l'application
+st.title('California Housing Prices Prediction')
+
+# Charger les données
+california = fetch_california_housing()
+df = pd.DataFrame(california.data, columns=california.feature_names)
+df['MedHouseVal'] = california.target # Valeur médiane des maisons
+
+# Afficher les données
+st.write("## Data Overview")
+st.write(df.head())
+
+# Visualiser les relations
+st.write("## Scatter Plot")
+fig, ax = plt.subplots()
+ax.scatter(df['AveRooms'], df['MedHouseVal'])
+ax.set_xlabel('Average number of rooms per dwelling')
+ax.set_ylabel('Median house value')
+st.pyplot(fig)
+
+# Sélectionner le prédicteur
+X = df[['AveRooms']]
+y = df['MedHouseVal']
+
+# Diviser les données en ensembles d'entraînement et de test
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+
+# Créer et entraîner le modèle de régression linéaire
+lr_model = LinearRegression()
+lr_model.fit(X_train, y_train)
+y_pred = lr_model.predict(X_test)
+
+# Évaluer la performance du modèle
+rmse = np.sqrt(mean_squared_error(y_test, y_pred))
+r2 = r2_score(y_test, y_pred)
+
+st.write(f'## Linear Regression Model Performance')
+st.write(f'RMSE: {rmse:.2f}')
+st.write(f'R-squared: {r2:.2f}')
+
+# Visualiser la ligne de régression
+st.write("## Regression Line")
+fig, ax = plt.subplots()
+ax.scatter(X_test['AveRooms'], y_test, color='blue')
+ax.plot(X_test['AveRooms'], y_pred, color='red')
+ax.set_xlabel('Average number of rooms per dwelling')
+ax.set_ylabel('Median house value')
+st.pyplot(fig)
+
+# Multirégression linéaire
+X = df.drop('MedHouseVal', axis=1)
+y = df['MedHouseVal']
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)
+mlr_model = LinearRegression()
+mlr_model.fit(X_train, y_train)
+y_pred = mlr_model.predict(X_test)
+
+rmse_ml = np.sqrt(mean_squared_error(y_test, y_pred))
+r2_ml = r2_score(y_test, y_pred)
+
+st.write(f'## Multilinear Regression Model Performance')
+st.write(f'RMSE: {rmse_ml:.2f}')
+st.write(f'R-squared: {r2_ml:.2f}')
+
+st.write("## Multilinear Regression Predictions")
+fig, ax = plt.subplots()
+ax.scatter(y_test, y_pred)
+ax.set_xlabel('Actual Median House Value')
+ax.set_ylabel('Predicted Median House Value')
+ax.set_title('Multilinear Regression Model Predictions')
+st.pyplot(fig)