batman

kaggle_machine_learning/main.py

@@ -0,0 +1,75 @@
+import pandas as pd
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_absolute_percentage_error
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+
+def get_accuracy(target, prediction):
+    error_percent = mean_absolute_percentage_error(target, prediction)
+    accuracy = round((1-error_percent)*100,2)
+    return accuracy
+
+def decision_tree(max_leaf_nodes, train_features, test_features, train_targets, test_targets):
+    model = DecisionTreeRegressor(max_leaf_nodes=max_leaf_nodes, random_state=0)
+    model.fit(train_features, train_targets)
+    predictions = model.predict(test_features)
+    return get_accuracy(test_targets, predictions)
+
+def random_forest(train_features, test_features, train_targets, test_targets):
+    model = RandomForestRegressor()
+    model.fit(train_features, train_targets)
+    predictions = model.predict(test_features)
+    return get_accuracy(test_targets, predictions)
+
+def linear_regreassion(train_features, test_features, train_targets, test_targets):
+    model = LinearRegression()
+    model.fit(train_features, train_targets)
+    predictions = model.predict(test_features)
+    return get_accuracy(test_targets, predictions)
+
+####### Melbourne Predicitons ########
+
+melbourne_data = pd.read_csv('melb_data.csv')
+melbourne_data = melbourne_data.dropna()
+# for column_name in melbourne_data.columns:
+#     print(column_name)
+melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'BuildingArea', 'YearBuilt', 'Lattitude', 'Longtitude']
+
+target = melbourne_data.Price
+features = melbourne_data[melbourne_features]
+train_features, test_features, train_targets, test_targets = train_test_split(features, target, random_state=3)
+
+print('\n\tMelbourne House Price Guessing')
+print('Decision Tree Accuracy')
+for max_leaf_nodes in [5,10,50,100,1000, 5000]:
+    melbourne_accuracy = decision_tree(max_leaf_nodes, train_features, test_features, train_targets, test_targets)
+    print(f'  max leaf nodes: {max_leaf_nodes}\t{melbourne_accuracy}%')
+melbourne_forest_accuracy = random_forest(train_features, test_features, train_targets, test_targets)
+print(f'Forest accuracy: {melbourne_forest_accuracy}%')
+melbourne_linear_accuracy = linear_regreassion(train_features, test_features, train_targets, test_targets)
+print(f'Regression accuracy: {melbourne_linear_accuracy}%')
+
+
+
+####### Iowa Predicitons ########
+
+iowa_data = pd.read_csv('train.csv')
+# for column_name in iowa_data.columns:
+#     print(column_name)
+# print(iowa_data.head())
+iowa_features = ['LotArea','YearBuilt','1stFlrSF','2ndFlrSF','FullBath','BedroomAbvGr','TotRmsAbvGrd']
+
+target = iowa_data.SalePrice
+features = iowa_data[iowa_features]
+train_features, test_features, train_targets, test_targets = train_test_split(features, target, random_state=3)
+
+print('\n\tIowa House Price Guessing')
+print('Decision Tree Accuracy')
+for max_leaf_nodes in [5,10,50,100,1000, 5000]:
+    iowa_accuracy = decision_tree(max_leaf_nodes, train_features, test_features, train_targets, test_targets)
+    print(f'  max leaf nodes: {max_leaf_nodes}\t{iowa_accuracy}%')
+iowa_forest_accuracy = random_forest(train_features, test_features, train_targets, test_targets)
+print(f'Forest accuracy: {iowa_forest_accuracy}%')
+iowa_linear_accuracy = linear_regreassion(train_features, test_features, train_targets, test_targets)
+print(f'Regression accuracy: {iowa_linear_accuracy}%')