app.py

import streamlit as st
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.datasets import fetch_california_housing
import pickle

from sklearn import datasets

from sklearn.metrics import mean_squared_error, r2_score

# Load the data
california = fetch_california_housing()
df = pd.DataFrame(california.data, columns=california.feature_names)
df['MedHouseVal'] = california.target

# Prepare the data for the model
X = df[['MedInc']]
y = df['MedHouseVal']

# Pairplot to visualize relationships between features and the target
plt.show()


plt.figure(figsize=(10, 8))
plt.show()

# Scatter plot for specific features against the target variable
features = ['MedInc', 'AveRooms', 'AveOccup', 'HouseAge']
for feature in features:
    plt.figure(figsize=(6, 4))
    plt.scatter(df[feature], df['MedHouseVal'], alpha=0.3)
    plt.title(f'MedHouseVal vs {feature}')
    plt.xlabel(feature)
    plt.ylabel('MedHouseVal')
    plt.show()
#5
# Select the predictor and target variable
X = df[['MedInc']]
y = df['MedHouseVal']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
print("Training and testing data split done.")

#6 7 and 8
#lineare regression model
model = LinearRegression()

# Fitting the model on the training data
model.fit(X_train, y_train)

# Making predictions on the test data
y_pred = model.predict(X_test)

# Evaluating the model
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y_test, y_pred)




# Plot the regression line
plt.figure(figsize=(8, 6))
plt.scatter(X_test, y_test, color='blue', alpha=0.3, label='Actual')
plt.plot(X_test, y_pred, color='red', linewidth=2, label='Predicted')
plt.title('Simple Linear Regression: MedInc vs MedHouseVal')
plt.xlabel('MedInc')
plt.ylabel('MedHouseVal')
plt.legend()
plt.show()

 #Split the data into training (80%) and testing (20%) sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Print the sizes of the training and testing sets
print(f"Training set size: {X_train.shape[0]} samples")
print(f"Testing set size: {X_test.shape[0]} samples")

# Create the linear regression model
model = LinearRegression()

# Fit the model on the training data
model.fit(X_train, y_train)

# Print the coefficients
print(f"Coefficients: {model.coef_}")
print(f"Intercept: {model.intercept_}")

# Make predictions on the test data
y_pred = model.predict(X_test)

# Calculate RMSE and R-squared
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y_test, y_pred)

print(f"Root Mean Squared Error (RMSE): {rmse}")
print(f"R-squared: {r2}")

# Scatter plot of actual vs. predicted values
plt.figure(figsize=(8, 6))
plt.scatter(y_test, y_pred, color='blue', alpha=0.3)
plt.plot([y_test.min(), y_test.max()], [y_test.min(), y_test.max()], 'k--', lw=2, color='green')
plt.title('Multilinear Regression: Actual vs. Predicted MedHouseVal')
plt.xlabel('Actual MedHouseVal')
plt.ylabel('Predicted MedHouseVal')
plt.show()

#comparing the performance between RMSE and R-squared values
# Simple Linear Regression
# Select a single predictor
X_single = df[['MedInc']]
y = df['MedHouseVal']

# Split the data into training and testing sets
X_train_single, X_test_single, y_train_single, y_test_single = train_test_split(X_single, y, test_size=0.2, random_state=42)

# Create the linear regression model
model_single = LinearRegression()

# Fit the model on the training data
model_single.fit(X_train_single, y_train_single)

# Make predictions on the test data
y_pred_single = model_single.predict(X_test_single)

# Evaluate the model
mse_single = mean_squared_error(y_test_single, y_pred_single)
rmse_single = np.sqrt(mse_single)
r2_single = r2_score(y_test_single, y_pred_single)

print(f"Simple Linear Regression - RMSE: {rmse_single}")
print(f"Simple Linear Regression - R-squared: {r2_single}")

# Multilinear Regression
# Select multiple predictors
X_multi = df[['MedInc', 'AveRooms', 'HouseAge', 'AveOccup']]
y = df['MedHouseVal']

# Split the data into training and testing sets
X_train_multi, X_test_multi, y_train_multi, y_test_multi = train_test_split(X_multi, y, test_size=0.2, random_state=42)

# Create the linear regression model
model_multi = LinearRegression()

# Fit the model on the training data
model_multi.fit(X_train_multi, y_train_multi)

# Make predictions on the test data
y_pred_multi = model_multi.predict(X_test_multi)

# Evaluate the model
mse_multi = mean_squared_error(y_test_multi, y_pred_multi)
rmse_multi = np.sqrt(mse_multi)
r2_multi = r2_score(y_test_multi, y_pred_multi)

print(f"Multilinear Regression - RMSE: {rmse_multi}")
print(f"Multilinear Regression - R-squared: {r2_multi}")

#Residual Plot for Multilinear Regression
residuals = y_test_multi - y_pred_multi
plt.figure(figsize=(8, 6))
plt.scatter(y_pred_multi, residuals, color='blue', alpha=0.3)
plt.hlines(y=0, xmin=y_pred_multi.min(), xmax=y_pred_multi.max(), colors='red', linestyles='--', lw=2)
plt.title('Residual Plot: Multilinear Regression')
plt.xlabel('Predicted MedHouseVal')
plt.ylabel('Residuals')
plt.show()

# Save the model
with open("linear_regression_model.pkl", "wb") as file:
    pickle.dump(model, file)

# Load the model
with open("linear_regression_model.pkl", "rb") as file:
    model = pickle.load(file)

# Sidebar for user input features
st.sidebar.header('User Input Features')
selected_feature = st.sidebar.selectbox('Select feature for visualization', df.columns)
selected_target = st.sidebar.selectbox('Select target variable', df.columns)


    st.write(df)

# Visualization of selected feature
st.subheader(f'Distribution of {selected_feature}')
fig, ax = plt.subplots()
ax.hist(df[selected_feature], bins=30, edgecolor='black')
st.pyplot(fig)

# Scatter plot of selected feature vs target
st.subheader(f'Scatter plot of {selected_feature} vs {selected_target}')
fig, ax = plt.subplots()
ax.scatter(df[selected_feature], df[selected_target], alpha=0.3)
ax.set_xlabel(selected_feature)
ax.set_ylabel(selected_target)



# Simple Linear Regression
X_single = df[['MedInc']]
y = df['MedHouseVal']

X_train_single, X_test_single, y_train_single, y_test_single = train_test_split(X_single, y, test_size=0.2, random_state=42)

model_single = LinearRegression()
model_single.fit(X_train_single, y_train_single)

y_pred_single = model_single.predict(X_test_single)

r2_single = r2_score(y_test_single, y_pred_single)

# Plot the regression line for simple linear regression
fig, ax = plt.subplots()
ax.scatter(X_test_single, y_test_single, color='blue', alpha=0.3, label='Actual')
ax.plot(X_test_single, y_pred_single, color='red', linewidth=2, label='Predicted')
ax.set_title('Simple Linear Regression: MedInc vs MedHouseVal')
ax.set_xlabel('MedInc')
ax.set_ylabel('MedHouseVal')
ax.legend()
st.pyplot(fig)

# Multilinear Regression
X_multi = df[['MedInc', 'AveRooms', 'HouseAge', 'AveOccup']]
y = df['MedHouseVal']

X_train_multi, X_test_multi, y_train_multi, y_test_multi = train_test_split(X_multi, y, test_size=0.2, random_state=42)

model_multi = LinearRegression()
model_multi.fit(X_train_multi, y_train_multi)

y_pred_multi = model_multi.predict(X_test_multi)

r2_multi = r2_score(y_test_multi, y_pred_multi)

# Show regression line if selected
show_regression = st.checkbox('Show Regression Line')
if show_regression and selected_feature in df.columns and selected_target == 'MedHouseVal':
    X_feature = df[[selected_feature]]
    y = df[selected_target]
    model_feature = LinearRegression()
    model_feature.fit(X_feature, y)
    line = model_feature.predict(X_feature)
    ax.plot(df[selected_feature], line, color='red', linewidth=2)

st.pyplot(fig)

# Add checkbox for multilinear regression plot
show_multilinear_plot = st.checkbox('Show Multilinear Regression Plot')

if show_multilinear_plot:
    fig, ax = plt.subplots()
    ax.scatter(y_test_multi, y_pred_multi, color='blue', alpha=0.3)
    ax.plot([y_test_multi.min(), y_test_multi.max()], [y_test_multi.min(), y_test_multi.max()], 'k--', lw=2, color='green')
    ax.set_title('Multilinear Regression: Actual vs. Predicted MedHouseVal')
    ax.set_xlabel('Actual MedHouseVal')
    ax.set_ylabel('Predicted MedHouseVal')
    st.pyplot(fig)

# Compare R-squared values
st.subheader('R-squared Comparison')
st.write(f"Simple Linear Regression R-squared: {r2_single:.4f}")
st.write(f"Multilinear Regression R-squared: {r2_multi:.4f}")

# Prediction
st.subheader('Predict Median House Value')

input_values = {}
for feature in X_multi.columns:
    input_values[feature] = st.number_input(f'Enter {feature}', value=float(df[feature].mean()))

if st.button('Predict'):
    input_data = np.array([list(input_values.values())])
    prediction = model_multi.predict(input_data)
    st.write(f'Predicted Median House Value: {prediction[0]}')