diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..7f7bf36 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..59da0e3 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..137a6b4 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..ef29bdd 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 +6,24 @@ 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): + dt_regressor = DecisionTreeRegressor(random_state=9) + grid_search = GridSearchCV(dt_regressor,param_grid=param_grid,cv=5) + + grid_search.fit(X_train,y_train) + predictions = grid_search.predict(X_test) + + return r2_score(y_test,predictions),grid_search.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..0333781 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..84feeb4 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..fba10b1 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..01af56e 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..6ef8ddd 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 @@ -6,8 +7,7 @@ import matplotlib.pyplot as plt 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 +15,27 @@ 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): + + errors_test = [] + errors_train = [] + for i in range(len(depth_list)): + dt_Reg = DecisionTreeRegressor(max_depth=depth_list[i],random_state=9) + dt_Reg.fit(X_train,y_train) + + preds_train = dt_Reg.predict(X_train) + preds_test = dt_Reg.predict(X_test) + + errors_train.append(mean_squared_error(y_train,preds_train)) + errors_test.append(mean_squared_error(y_test,preds_test)) + + plt.plot(depth_list,errors_train,label='Train Error') + plt.plot(depth_list,errors_test,label='Test Error') + plt.legend() + plt.ylabel('Mean Squared Error') + plt.xlabel('Max Depth') + plt.show() +decision_regressor_plot(X_train,X_test,y_train,y_test,depth_list) + + + 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..3a22624 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..41e777b 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..bf2fca5 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..a064d90 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..bad931a 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 +7,25 @@ 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): + dt_reg = DecisionTreeClassifier(random_state=9) + random_cv = RandomizedSearchCV(dt_reg,param_distributions=param_grid,n_iter=n_iter_search) + + random_cv.fit(X_train,y_train) + return accuracy_score(y_test,random_cv.predict(X_test)),random_cv.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..88109b8 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..21ac84c 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..eae1cca 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..6609bc0 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..7965586 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 @@ -8,7 +9,7 @@ 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] @@ -18,3 +19,22 @@ # Write your solution here : +def decision_classifier_plot(X_train,X_test,y_train,y_test,depth_list): + error_train = [] + error_test = [] + for i in range(len(depth_list)): + dt_classifier = DecisionTreeClassifier(max_depth=depth_list[i],random_state=9) + dt_classifier.fit(X_train,y_train) + predict_train = dt_classifier.predict(X_train) + predict_test = dt_classifier.predict(X_test) + + error_train.append(accuracy_score(y_train,predict_train)) + + error_test.append(accuracy_score(y_test,predict_test)) + + + plt.plot(depth_list,error_test) + plt.plot(depth_list,error_train) + 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..74096bf 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..06ddc28 Binary files /dev/null and b/q04_decision_classifier_plot/tests/__pycache__/test_q04_decision_classifier_plot.cpython-36.pyc differ