diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..9f4251c 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..c6bc4db 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..7f26677 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..c746e67 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 +6,23 @@ 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): + model=DecisionTreeRegressor(random_state=9) + grid_search = GridSearchCV(model,param_grid=param_grid,cv=5) + grid_search.fit(X_train,y_train) + y_prediction = grid_search.predict(X_test) + r_square=r2_score(y_test,y_prediction) + best_params=grid_search.best_params_ + return r_square,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..d8478f1 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..e161873 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..e78832b 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..3785020 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..11783d6 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 +16,27 @@ 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,depths): + train_results=[] + test_results=[] + depth_list = [2, 8, 10, 15, 20, 25, 30, 35, 45, 50, 80] + for depth_list in depth_list: + model=DecisionTreeRegressor(random_state=9,max_depth=depth_list) + model.fit(X_train,y_train) + train_pred=model.predict(X_train) + mse_train=mean_squared_error(y_train,train_pred) + train_results.append(mse_train) + + test_pred=model.predict(X_test) + mse_test=mean_squared_error(y_test,test_pred) + test_results.append(mse_test) + + plt.plot([2, 8, 10, 15, 20, 25, 30, 35, 45, 50, 80],train_results,'b-',label='Train set') + plt.plot([2, 8, 10, 15, 20, 25, 30, 35, 45, 50, 80],test_results,'g-',label='Test set') + plt.legend(loc='best') + plt.xlabel('depths') + plt.ylabel('mean squared 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..3aaa1c1 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..0cf55fc 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..6b2d5e8 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..364f612 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..f1f8899 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): + model=DecisionTreeClassifier(random_state=9) + random_search = RandomizedSearchCV(model,param_distributions=param_grid,n_iter=n_iter_search) + random_search.fit(X_train,y_train) + y_prediction = random_search.predict(X_test) + accuracy=accuracy_score(y_test,y_prediction) + best_params=random_search.best_params_ + return accuracy,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..3b4fdd9 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..bf6a4b3 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..2fd29f5 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..e4eaa7e 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..0756968 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 +19,27 @@ # Write your solution here : +def decision_classifier_plot(X_train,X_test,y_train,y_test,depths): + train_results=[] + test_results=[] + depth_list = [8, 10, 15, 20, 50, 100, 120, 150, 175, 200] + for depth_list in depth_list: + model=DecisionTreeClassifier(random_state=9,max_depth=depth_list) + model.fit(X_train,y_train) + train_pred=model.predict(X_train) + accuracy=accuracy_score(y_train,train_pred) + train_results.append(accuracy) + + test_pred=model.predict(X_test) + accuracy1=accuracy_score(y_test,test_pred) + test_results.append(accuracy1) + + plt.plot([8, 10, 15, 20, 50, 100, 120, 150, 175, 200],train_results,'b-',label='Train set') + plt.plot([8, 10, 15, 20, 50, 100, 120, 150, 175, 200],test_results,'g-',label='Test set') + plt.legend(loc='best') + plt.xlabel('depths') + plt.ylabel('mean accuracy score') + 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..a18ab98 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..6e2cdb2 Binary files /dev/null and b/q04_decision_classifier_plot/tests/__pycache__/test_q04_decision_classifier_plot.cpython-36.pyc differ