import pandas as pd from sklearn.ensemble import RandomForestRegressor from sklearn.metrics import mean_absolute_error from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeRegressor import matplotlib.pyplot as plt

# Path of the file to read iowa_file_path = '/work/ML kaggle learn/Data_ML_try/Housing Prices/train.csv' home_data = pd.read_csv(iowa_file_path) # Create target object and call it y y = home_data.SalePrice # Create X features = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd'] X = home_data[features]

# Split into validation and training data train_X, val_X, train_y, val_y = train_test_split(X, y, random_state=1)

# Specify Model iowa_model = DecisionTreeRegressor(random_state=1) # Fit Model iowa_model.fit(train_X, train_y) # Make validation predictions and calculate mean absolute error val_predictions = iowa_model.predict(val_X) val_mae = mean_absolute_error(val_predictions, val_y) print("Validation MAE when not specifying max_leaf_nodes: {:,.0f}".format(val_mae))

# Using best value for max_leaf_nodes iowa_model = DecisionTreeRegressor(max_leaf_nodes=100, random_state=1) iowa_model.fit(train_X, train_y) val_predictions = iowa_model.predict(val_X) val_mae = mean_absolute_error(val_predictions, val_y) print("Validation MAE for best value of max_leaf_nodes: {:,.0f}".format(val_mae))

# To improve accuracy, create a new Random Forest model which you will train on all training data rf_model_on_full_data = RandomForestRegressor(n_estimators=100, max_depth=10, random_state=0) # fit rf_model_on_full_data on all data from the training data rf_model_on_full_data.fit(X, y) # path to file you will use for predictions test_data_path = '/work/ML kaggle learn/Data_ML_try/Housing Prices/test.csv' # read test data file using pandas test_data = pd.read_csv(test_data_path) # create test_X which comes from test_data but includes only the columns you used for prediction. # The list of columns is stored in a variable called features test_X = test_data[features] # make predictions which we will submit. test_preds = rf_model_on_full_data.predict(test_X) # Create a DataFrame of predictions output = pd.DataFrame({'Id': test_data.Id, 'SalePrice': test_preds}) # Save the predictions to a CSV file output.to_csv('submission.csv', index=False)

import seaborn as sns # combine the training features and target variable into a single DataFrame train_data = pd.concat([train_X, train_y], axis=1) # create a scatter plot matrix for the selected features and target variable sns.pairplot(train_data, y_vars=['SalePrice'], x_vars=['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd'])

# Create a grid of scatter plots for each feature vs SalePrice fig, axes = plt.subplots(nrows=2, ncols=4, figsize=(12, 8)) for idx, feature in enumerate(features): ax = axes[int(idx / 4), idx % 4] ax.scatter(train_X[feature], train_y, s=6) # set the size of the dots with the s part ax.set_xlabel(feature) ax.set_ylabel('SalePrice') # plt.tight_layout() # adjust spacing between subplots for better readability plt.show()

import numpy as np # Create a correlation matrix corr_matrix = home_data.corr() # Create a mask for the upper triangle mask = np.triu(np.ones_like(corr_matrix, dtype=bool)) # Set up the matplotlib figure fig, ax = plt.subplots(figsize=(12, 10)) # Generate a custom diverging colormap cmap = sns.diverging_palette(230, 20, as_cmap=True) # Draw the heatmap with the mask and correct aspect ratio sns.heatmap(corr_matrix, mask=mask, cmap=cmap, vmax=3, center=0, square=True, linewidths=.9, cbar_kws={"shrink": .9}) plt.title("Correlation matrix plot") plt.show()

corr_matrix = train_data.corr() sns.heatmap(corr_matrix, annot=True, cmap='Blues') plt.show()

sns.violinplot(x=home_data['OverallQual'], y=train_data['SalePrice']) plt.show()

sns.boxplot(x=home_data['OverallQual'], y=train_data['SalePrice']) plt.show()

sns.boxplot(x=home_data['SaleCondition'], y=train_data['SalePrice']) plt.show()

from sklearn.tree import plot_tree plt.figure(figsize=(30,10)) plot_tree(iowa_model, filled=True, feature_names=X.columns) plt.show()

plt.hist(train_data['SalePrice'], bins=20) plt.xlabel('Sale Price') plt.ylabel('Frequency') plt.title('Histogram of Sale Prices') plt.show()

import matplotlib.pyplot as plt plt.hist(train_X['LotArea'], bins=20) plt.title('Distribution of Lot Area') plt.xlabel('Lot Area (sqft)') plt.ylabel('Count') plt.show()