<\/p>\n\n\n\n
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
# ============================================
# Part 1: Load and Prepare Dataset
# ============================================
# Given dataset
data = {
\"Storage\": [32, 32, 64, 64, 128, 128, 128, 256, 256, 256, 512, 512, 512, 512, 512],
\"Price\": [10, 12, 15, 18, 22, 25, 30, 35, 38, 42, 50, 55, 60, 65, 70]
}
# Convert to DataFrame
df_phones = pd.DataFrame(data)
print(\"=\"*60)
print(\"Q2: Smartphone Price Prediction - Linear Regression\")
print(\"=\"*60)
print(\"\\n Dataset Overview:\")
print(df_phones.head(10))
print(f\"\\n Dataset Shape: {df_phones.shape}\")
print(f\" Storage Range: {df_phones['Storage'].min()}GB - {df_phones['Storage'].max()}GB\")
print(f\" Price Range: \u20b9{df_phones['Price'].min()}K - \u20b9{df_phones['Price'].max()}K\")
# Check for any missing values
print(f\"\\n Missing Values:\\n{df_phones.isnull().sum()}\")
# ============================================
# Part 2: Split Features and Target
# ============================================
# Independent variable (X) - Storage
X = df_phones[['Storage']] # 2D array (required by sklearn)
# Dependent variable (y) - Price
y = df_phones['Price'] # 1D array
print(\"\\n Feature (Independent Variable): Storage\")
print(f\"Shape: {X.shape}\")
print(\"\\n Target (Dependent Variable): Price\")
print(f\"Shape: {y.shape}\")
# ============================================
# Part 3: Split into Training and Testing Sets
# ============================================
# Split data: 80% training, 20% testing
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
print(f\"\\n Training Set Size: {len(X_train)} samples\")
print(f\" Testing Set Size: {len(X_test)} samples\")
# ============================================
# Part 4: Build and Train Linear Regression Model
# ============================================
# Create and train the model
model = LinearRegression()
model.fit(X_train, y_train)
# Get model coefficients
print(f\"\\n Model Coefficients:\")
print(f\"Intercept (\u03b20): {model.intercept_:.4f}\")
print(f\"Coefficient (\u03b21): {model.coef_[0]:.4f}\")
print(f\"\\n Equation: Price = {model.intercept_:.2f} + {model.coef_[0]:.2f} * Storage\")
# ============================================
# Part 5: Predict Prices
# ============================================
# Predict on training and test data
y_train_pred = model.predict(X_train)
y_test_pred = model.predict(X_test)
# Predict for new storage values (Indian market scenario)
new_storage = np.array([[64], [128], [256], [512], [1024]])
predicted_prices = model.predict(new_storage)
print(\"\\n Predictions for New Storage Options:\")
predictions_df = pd.DataFrame({
'Storage (GB)': new_storage.flatten(),
'Predicted Price (\u20b9K)': np.round(predicted_prices, 2)
})
print(predictions_df)
# ============================================
# Part 6: Visualize Regression Line on Scatter Plot
# ============================================
plt.figure(figsize=(12, 6))
# Scatter plot of actual data
plt.scatter(X, y, color='blue', s=100, alpha=0.6, label='Actual Data', edgecolors='black')
# Regression line
x_range = np.linspace(X.min(), X.max(), 100).reshape(-1, 1)
y_range = model.predict(x_range)
plt.plot(x_range, y_range, color='red', linewidth=3, label='Regression Line')
# Highlight training and test points
plt.scatter(X_train, y_train, color='green', s=80, alpha=0.5, marker='o', label='Training Data')
plt.scatter(X_test, y_test, color='orange', s=120, alpha=0.7, marker='s', label='Test Data')
# Plot predictions
plt.scatter(new_storage, predicted_prices, color='purple', s=200, marker='D',
label='Predicted for New Storage', edgecolors='black', zorder=5)
# Add value labels for predictions
for i, (storage, price) in enumerate(zip(new_storage.flatten(), predicted_prices)):
plt.annotate(f'{storage}GB: \u20b9{price:.1f}K',
(storage, price),
xytext=(10, 10),
textcoords='offset points',
fontsize=9,
bbox=dict(boxstyle='round,pad=0.3', facecolor='yellow', alpha=0.7))
# Customize plot
plt.xlabel('Storage (GB)', fontsize=12)
plt.ylabel('Price (\u20b9K)', fontsize=12)
plt.title('Smartphone Price Prediction\\nStorage vs Price (Linear Regression)', fontsize=14, fontweight='bold')
plt.legend(loc='upper left', fontsize=10)
plt.grid(True, alpha=0.3)
plt.xlim(0, 1100)
plt.ylim(0, 120)
# Add annotation for model equation
plt.text(550, 20, f'Price = {model.intercept_:.2f} + {model.coef_[0]:.2f} * Storage',
fontsize=11, bbox=dict(boxstyle='round,pad=0.5', facecolor='lightgray', alpha=0.8))
plt.show()
# ============================================
# Part 7: Evaluate Model Performance
# ============================================
print(\"\\n\" + \"=\"*60)
print(\"PART 5: Model Evaluation\")
print(\"=\"*60)
# R\u00b2 Score
r2_train = r2_score(y_train, y_train_pred)
r2_test = r2_score(y_test, y_test_pred)
print(f\"\\n R\u00b2 Score (Training): {r2_train:.4f}\")
print(f\" R\u00b2 Score (Testing): {r2_test:.4f}\")
# Other metrics
mse_train = mean_squared_error(y_train, y_train_pred)
mse_test = mean_squared_error(y_test, y_test_pred)
rmse_train = np.sqrt(mse_train)
rmse_test = np.sqrt(mse_test)
mae_train = mean_absolute_error(y_train, y_train_pred)
mae_test = mean_absolute_error(y_test, y_test_pred)
print(f\"\\n Training Metrics:\")
print(f\" MSE: {mse_train:.4f}\")
print(f\" RMSE: {rmse_train:.4f}\")
print(f\" MAE: {mae_train:.4f}\")
print(f\"\\n Testing Metrics:\")
print(f\" MSE: {mse_test:.4f}\")
print(f\" RMSE: {rmse_test:.4f}\")
print(f\" MAE: {mae_test:.4f}\")
# ============================================
# Part 8: Residual Analysis
# ============================================
# Calculate residuals
residuals = y_test - y_test_pred
# Plot residuals
plt.figure(figsize=(12, 5))
plt.subplot(1, 2, 1)
plt.scatter(y_test_pred, residuals, color='purple', alpha=0.7, s=80)
plt.axhline(y=0, color='red', linestyle='--', linewidth=2)
plt.xlabel('Predicted Price (\u20b9K)', fontsize=12)
plt.ylabel('Residuals', fontsize=12)
plt.title('Residual Plot', fontsize=12)
plt.grid(True, alpha=0.3)
plt.subplot(1, 2, 2)
plt.hist(residuals, bins=8, color='lightgreen', edgecolor='black', alpha=0.7)
plt.xlabel('Residuals', fontsize=12)
plt.ylabel('Frequency', fontsize=12)
plt.title('Distribution of Residuals', fontsize=12)
plt.axvline(x=0, color='red', linestyle='--', linewidth=2)
plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()
# ============================================
# Part 9: Real-world Indian Market Insights
# ============================================
print(\"\\n\" + \"=\"*60)
print(\"Real-World Indian Market Insights\")
print(\"=\"*60)
# Predict prices for popular Indian smartphone configurations
indian_configs = np.array([[64], [128], [256], [512]])
indian_prices = model.predict(indian_configs)
print(\"\\n Predicted Prices for Indian Smartphone Configurations:\")
config_data = pd.DataFrame({
'Storage': indian_configs.flatten(),
'Predicted Price (\u20b9K)': np.round(indian_prices, 2),
'Predicted Price (\u20b9)': np.round(indian_prices * 1000, 0)
})
print(config_data)
print(\"\\n Price Comparison:\")
print(\"64GB: \u20b915,000 - \u20b918,000 (Budget segment)\")
print(\"128GB: \u20b922,000 - \u20b930,000 (Mid-range)\")
print(\"256GB: \u20b935,000 - \u20b942,000 (Premium)\")
print(\"512GB: \u20b950,000 - \u20b970,000 (Flagship)\")
print(\"\\n Model Training and Evaluation Complete!\")<\/pre>\n","protected":false},"excerpt":{"rendered":"import pandas as pdimport numpy as npimport matplotlib.pyplot as pltfrom sklearn.model_selection import train_test_splitfrom sklearn.linear_model import LinearRegressionfrom sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error# ============================================# Part 1: Load and Prepare Dataset# ============================================# Given datasetdata = { “Storage”: [32, 32, 64, 64, 128, 128, 128, 256, 256, 256, 512, 512, 512, 512, 512], “Price”: [10, 12, 15, 18, 22, […]<\/p>\n","protected":false},"author":1,"featured_media":188,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3,55],"tags":[25,26,59,58,45],"class_list":["post-198","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-bca","category-ml","tag-bca","tag-bca-paper-solution","tag-machine-learning","tag-ml","tag-python"],"_links":{"self":[{"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/posts\/198","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/comments?post=198"}],"version-history":[{"count":1,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/posts\/198\/revisions"}],"predecessor-version":[{"id":199,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/posts\/198\/revisions\/199"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/media\/188"}],"wp:attachment":[{"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/media?parent=198"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/categories?post=198"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/alpeshconnect.in\/blog\/wp-json\/wp\/v2\/tags?post=198"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}