diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..4562db9 Binary files /dev/null and b/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_my_decision_regressor/__pycache__/__init__.cpython-36.pyc b/q01_my_decision_regressor/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..f67e3b6 Binary files /dev/null and b/q01_my_decision_regressor/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_my_decision_regressor/__pycache__/build.cpython-36.pyc b/q01_my_decision_regressor/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000..c54bf9b Binary files /dev/null and b/q01_my_decision_regressor/__pycache__/build.cpython-36.pyc differ diff --git a/q01_my_decision_regressor/build.py b/q01_my_decision_regressor/build.py index 5eb1927..c34a667 100644 --- a/q01_my_decision_regressor/build.py +++ b/q01_my_decision_regressor/build.py @@ -1,3 +1,4 @@ +# %load q01_my_decision_regressor/build.py # default imports from sklearn.model_selection import GridSearchCV from sklearn.tree import DecisionTreeRegressor @@ -5,13 +6,22 @@ from sklearn.model_selection import train_test_split import pandas as pd -data = pd.read_csv("./data/house_pricing.csv") +data = pd.read_csv('./data/house_pricing.csv') X = data.iloc[:, :-1] y = data.iloc[:, -1] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=9) -param_grid = {"max_depth": [2, 3, 5, 6, 8, 10, 15, 20, 30, 50], - "max_leaf_nodes": [2, 3, 4, 5, 10, 15, 20], - "max_features": [4, 8, 20, 25]} +param_grid = {'max_depth': [2, 3, 5, 6, 8, 10, 15, 20, 30, 50], + 'max_leaf_nodes': [2, 3, 4, 5, 10, 15, 20], + 'max_features': [4, 8, 20, 25]} + +def my_decision_regressor(X_train, X_test, y_train, y_test, param_grid): + model = DecisionTreeRegressor(random_state=9) + grid_search_cv = GridSearchCV(model, param_grid, cv=5) + grid_search_cv.fit(X_train, y_train) + best_model = grid_search_cv.best_estimator_ + best_model.fit(X_train, y_train) + y_pred = best_model.predict(X_test) + return r2_score(y_test, y_pred), grid_search_cv.best_params_ + -# Write your solution here : diff --git a/q01_my_decision_regressor/tests/__pycache__/__init__.cpython-36.pyc b/q01_my_decision_regressor/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..bede5ec Binary files /dev/null and b/q01_my_decision_regressor/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_my_decision_regressor/tests/__pycache__/test_q01_my_decision_regressor.cpython-36.pyc b/q01_my_decision_regressor/tests/__pycache__/test_q01_my_decision_regressor.cpython-36.pyc new file mode 100644 index 0000000..12e9cb9 Binary files /dev/null and b/q01_my_decision_regressor/tests/__pycache__/test_q01_my_decision_regressor.cpython-36.pyc differ diff --git a/q02_decision_regressor_plot/__pycache__/__init__.cpython-36.pyc b/q02_decision_regressor_plot/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..2620d5c Binary files /dev/null and b/q02_decision_regressor_plot/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_decision_regressor_plot/__pycache__/build.cpython-36.pyc b/q02_decision_regressor_plot/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000..f62d25d Binary files /dev/null and b/q02_decision_regressor_plot/__pycache__/build.cpython-36.pyc differ diff --git a/q02_decision_regressor_plot/build.py b/q02_decision_regressor_plot/build.py index 02a9233..6863e8b 100644 --- a/q02_decision_regressor_plot/build.py +++ b/q02_decision_regressor_plot/build.py @@ -1,3 +1,4 @@ +# %load q02_decision_regressor_plot/build.py # default imports from sklearn.model_selection import train_test_split from sklearn.tree import DecisionTreeRegressor @@ -6,11 +7,27 @@ import matplotlib.pyplot as plt import numpy as np -data = pd.read_csv("./data/house_pricing.csv") +data = pd.read_csv('./data/house_pricing.csv') X = data.iloc[:, :-1] y = data.iloc[:, -1] X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=9) depth_list = [2, 8, 10, 15, 20, 25, 30, 35, 45, 50, 80] -# Write your solution here : +def decision_regressor_plot(X_train, X_test, y_train, y_test, depths): + train_scores = [] + test_scores = [] + for depth in depths: + model = DecisionTreeRegressor(criterion='mse', max_depth=depth, random_state=9) + model = model.fit(X_train, y_train) + y_pred_train = model.predict(X_train) + mse_train = mean_squared_error(y_pred_train, y_train) + train_scores.append(mse_train) + y_pred_test = model.predict(X_test) + mse_test = mean_squared_error(y_pred_test, y_test) + test_scores.append(mse_test) + plt.plot(depth_list, train_scores) + plt.plot(depth_list, test_scores) + plt.show() + + diff --git a/q02_decision_regressor_plot/tests/__pycache__/__init__.cpython-36.pyc b/q02_decision_regressor_plot/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..ee89643 Binary files /dev/null and b/q02_decision_regressor_plot/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_decision_regressor_plot/tests/__pycache__/test_q02_decision_regressor_plot.cpython-36.pyc b/q02_decision_regressor_plot/tests/__pycache__/test_q02_decision_regressor_plot.cpython-36.pyc new file mode 100644 index 0000000..b97f831 Binary files /dev/null and b/q02_decision_regressor_plot/tests/__pycache__/test_q02_decision_regressor_plot.cpython-36.pyc differ