diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..a0c088c 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..915427a 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..adf1458 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..23bdc78 100644 --- a/q01_my_decision_regressor/build.py +++ b/q01_my_decision_regressor/build.py @@ -1,17 +1,31 @@ +# %load q01_my_decision_regressor/build.py # default imports from sklearn.model_selection import GridSearchCV from sklearn.tree import DecisionTreeRegressor from sklearn.metrics import r2_score from sklearn.model_selection import train_test_split import pandas as pd - -data = pd.read_csv("./data/house_pricing.csv") +import numpy as np +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): + np.random.seed(9) + classifier = DecisionTreeRegressor(random_state=9) + best_params = GridSearchCV(classifier,param_grid=param_grid,cv = 5) + best_params.fit(X_train,y_train) + best_params1 = best_params.best_params_ + + y_pred = best_params.best_estimator_.predict(X_test) + + r2 = r2_score(y_test,y_pred) + return r2,best_params1 + + 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..1964ddd 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..b6e50f9 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..7bf2009 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..006014d 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..6d3a097 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 @@ -5,9 +6,10 @@ import pandas as pd import matplotlib.pyplot as plt import numpy as np +from sklearn.metrics import accuracy_score 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 +17,23 @@ 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): + mean_test_scores = [] + mean_train_scores = [] + for depth in depths: + dt_regressor = DecisionTreeRegressor(max_depth=depth) + dt_regressor.fit(X_train, y_train) + mse_train = mean_squared_error(y_train, dt_regressor.predict(X_train)) + mse_test = mean_squared_error(y_test, dt_regressor.predict(X_test)) + mean_test_scores.append(mse_test) + mean_train_scores.append(mse_train) + + plt.figure(figsize=(10, 6)) + plt.plot(depths, mean_train_scores, c='b', label='Train set') + plt.plot(depths, mean_test_scores, c='g', label='Test set') + plt.legend(loc='upper left') + plt.xlabel('depths') + plt.ylabel('mean square error') + 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..0d0a137 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..0f7dceb 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..ed05f10 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..c81beea 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..8e031b2 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): + clf = DecisionTreeClassifier(random_state=9) + random_search = RandomizedSearchCV(clf, param_distributions=param_grid,n_iter=n_iter_search) + random_search.fit(X_train,y_train) + best_param = random_search.best_params_ + y_pred = random_search.predict(X_test) + score = accuracy_score(y_test,y_pred) + return score,best_param + + 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..4a2d078 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..ffd40b6 Binary files /dev/null and b/q03_my_decision_classifier/tests/__pycache__/test_q03_my_decision_classifier.cpython-36.pyc differ diff --git a/q04_decision_classifier_plot/__pycache__/__init__.cpython-36.pyc b/q04_decision_classifier_plot/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..4ce6fa6 Binary files /dev/null and b/q04_decision_classifier_plot/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_decision_classifier_plot/__pycache__/build.cpython-36.pyc b/q04_decision_classifier_plot/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000..935e405 Binary files /dev/null and b/q04_decision_classifier_plot/__pycache__/build.cpython-36.pyc differ diff --git a/q04_decision_classifier_plot/build.py b/q04_decision_classifier_plot/build.py index 44e9e87..fe5bc52 100644 --- a/q04_decision_classifier_plot/build.py +++ b/q04_decision_classifier_plot/build.py @@ -1,3 +1,4 @@ +# %load q04_decision_classifier_plot/build.py # default imports from sklearn.model_selection import RandomizedSearchCV from sklearn.tree import DecisionTreeClassifier @@ -8,13 +9,34 @@ import numpy as np plt.switch_backend('agg') -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) -depth_list = [8, 10, 15, 20, 50, 100, 120, 150, 175, 200] +depth = [8, 10, 15, 20, 50, 100, 120, 150, 175, 200] # Write your solution here : +def decision_classifier_plot(X_train, X_test, y_train, y_test, depths): + mean_test_scores = [] + mean_train_scores = [] + + for depth in depths: + dt_classifier = DecisionTreeClassifier(max_depth=depth) + dt_classifier.fit(X_train, y_train) + acc_train = accuracy_score(y_train, dt_classifier.predict(X_train)) + acc_test = accuracy_score(y_test, dt_classifier.predict(X_test)) + mean_test_scores.append(acc_test) + mean_train_scores.append(acc_train) + + plt.figure(figsize=(10, 6)) + plt.plot(depths, mean_train_scores, c='b', label='Train set') + plt.plot(depths, mean_test_scores, c='g', label='Test set') + plt.legend(loc='upper left') + plt.xlabel('depths') + plt.ylabel('mean square error') + plt.show() + + diff --git a/q04_decision_classifier_plot/tests/__pycache__/__init__.cpython-36.pyc b/q04_decision_classifier_plot/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..df9bcc4 Binary files /dev/null and b/q04_decision_classifier_plot/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_decision_classifier_plot/tests/__pycache__/test_q04_decision_classifier_plot.cpython-36.pyc b/q04_decision_classifier_plot/tests/__pycache__/test_q04_decision_classifier_plot.cpython-36.pyc new file mode 100644 index 0000000..4d488b1 Binary files /dev/null and b/q04_decision_classifier_plot/tests/__pycache__/test_q04_decision_classifier_plot.cpython-36.pyc differ