diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..6c72c8b 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..c96a758 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..c132d6f 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..169b0ae 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 +6,29 @@ 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]} # Write your solution here : +def my_decision_regressor(X_train, X_test, y_train, y_test, param_grid): + + dtr = DecisionTreeRegressor(random_state=9) + + gscv = GridSearchCV(estimator=dtr, param_grid=param_grid, cv=5) + + gscv.fit(X_train, y_train) + + y_pred = gscv.predict(X_test) + + score = r2_score(y_test, y_pred) + + return score, gscv.best_params_ + + + 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..6937003 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..cf347c9 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..82505fd 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..2eddfee 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 020d81e..34ded28 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 @@ -7,7 +8,7 @@ import numpy as np plt.switch_backend('agg') -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) @@ -15,3 +16,18 @@ 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, depth_list): + + mean_squared_errors = list() + + for depth in depth_list: + dtr = DecisionTreeRegressor() + dtr.fit(X_train, y_train) + y_pred = dtr.predict(X_test) + mean_squared_errors.append(mean_squared_error(y_test, y_pred)) + + plt.plot(depth_list, mean_squared_errors) + + + + 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..8958f0b 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..6012a8d Binary files /dev/null and b/q02_decision_regressor_plot/tests/__pycache__/test_q02_decision_regressor_plot.cpython-36.pyc differ diff --git a/q03_my_decision_classifier/__pycache__/__init__.cpython-36.pyc b/q03_my_decision_classifier/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..1604dc4 Binary files /dev/null and b/q03_my_decision_classifier/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_my_decision_classifier/__pycache__/build.cpython-36.pyc b/q03_my_decision_classifier/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000..170ef4d Binary files /dev/null and b/q03_my_decision_classifier/__pycache__/build.cpython-36.pyc differ diff --git a/q03_my_decision_classifier/build.py b/q03_my_decision_classifier/build.py index 73c9856..edc5a0e 100644 --- a/q03_my_decision_classifier/build.py +++ b/q03_my_decision_classifier/build.py @@ -1,3 +1,4 @@ +# %load q03_my_decision_classifier/build.py # default imports from sklearn.model_selection import RandomizedSearchCV from sklearn.tree import DecisionTreeClassifier @@ -6,16 +7,26 @@ import pandas as pd import numpy as np -data = pd.read_csv("./data/loan_prediction.csv") +data = pd.read_csv('./data/loan_prediction.csv') np.random.seed(9) 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": [8, 10, 15, 20], - "max_leaf_nodes": [2, 5, 9, 15, 20], - "max_features": [1, 2, 3, 5]} - +param_grid = {'max_depth': [8, 10, 15, 20], + 'max_leaf_nodes': [2, 5, 9, 15, 20], + 'max_features': [1, 2, 3, 5]} # Write your solution here : +def my_decision_classifier(X_train, X_test, y_train, y_test, param_grid, n_iter_search=10): + + dtc = DecisionTreeClassifier(random_state=9) + + rscv = RandomizedSearchCV(dtc, param_distributions=param_grid, n_iter=n_iter_search) + + rscv.fit(X_train, y_train) + + return rscv.score(X_test, y_test) ,rscv.best_params_ + + diff --git a/q03_my_decision_classifier/tests/__pycache__/__init__.cpython-36.pyc b/q03_my_decision_classifier/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..220d9af Binary files /dev/null and b/q03_my_decision_classifier/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_my_decision_classifier/tests/__pycache__/test_q03_my_decision_classifier.cpython-36.pyc b/q03_my_decision_classifier/tests/__pycache__/test_q03_my_decision_classifier.cpython-36.pyc new file mode 100644 index 0000000..2596797 Binary files /dev/null and b/q03_my_decision_classifier/tests/__pycache__/test_q03_my_decision_classifier.cpython-36.pyc differ