diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index ebbd53a..2cc169e 100644 Binary files a/__pycache__/__init__.cpython-36.pyc and b/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc index 745b533..4f5f677 100644 Binary files a/q01_load_data/__pycache__/__init__.cpython-36.pyc and b/q01_load_data/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc index 108e4a3..4536b40 100644 Binary files a/q01_load_data/__pycache__/build.cpython-36.pyc and b/q01_load_data/__pycache__/build.cpython-36.pyc differ diff --git a/q01_load_data/build.py b/q01_load_data/build.py index e4cd8e3..f3d8679 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,10 +1,20 @@ +# %load q01_load_data/build.py # Default imports import pandas as pd from sklearn.model_selection import train_test_split - path = 'data/house_prices_multivariate.csv' - # Write your solution here +def load_data(path,test_size = 0.33,Random_state= 9): + df = pd.read_csv(path) + X = df.iloc[:,:-1] + y = df['SalePrice'] + X_train, X_test, y_train, y_test = train_test_split(X, y, random_state = Random_state, test_size= test_size) + return df, X_train,X_test,y_train,y_test + + + + + diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc index 133357e..414cc95 100644 Binary files a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc and b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc b/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc index 689755b..689d012 100644 Binary files a/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc and b/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc differ diff --git a/q02_Max_important_feature/__pycache__/__init__.cpython-36.pyc b/q02_Max_important_feature/__pycache__/__init__.cpython-36.pyc index 93c9119..2231f57 100644 Binary files a/q02_Max_important_feature/__pycache__/__init__.cpython-36.pyc and b/q02_Max_important_feature/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_Max_important_feature/__pycache__/build.cpython-36.pyc b/q02_Max_important_feature/__pycache__/build.cpython-36.pyc index 2b7cfd4..2eab325 100644 Binary files a/q02_Max_important_feature/__pycache__/build.cpython-36.pyc and b/q02_Max_important_feature/__pycache__/build.cpython-36.pyc differ diff --git a/q02_Max_important_feature/build.py b/q02_Max_important_feature/build.py index 51fbde6..2da3d4f 100644 --- a/q02_Max_important_feature/build.py +++ b/q02_Max_important_feature/build.py @@ -1,8 +1,19 @@ +# %load q02_Max_important_feature/build.py # Default imports from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data - +import numpy as np # We have already loaded the data for you data_set, X_train, X_test, y_train, y_test = load_data('data/house_prices_multivariate.csv') +df = data_set +target_variable = 'SalePrice' +# Write your code here +def Max_important_feature(data_set,target_variable = 'SalePrice' , n=4): + a = data_set.corr()[target_variable] + b = a.sort_values(axis=0, ascending=False, inplace=False, kind='quicksort', na_position='last') + c = list(np.array(b.index[1:n+1])) + return c + + + -# Write your code here diff --git a/q02_Max_important_feature/tests/__pycache__/__init__.cpython-36.pyc b/q02_Max_important_feature/tests/__pycache__/__init__.cpython-36.pyc index cec58d4..3753192 100644 Binary files a/q02_Max_important_feature/tests/__pycache__/__init__.cpython-36.pyc and b/q02_Max_important_feature/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_Max_important_feature/tests/__pycache__/test_q02max_important_feature.cpython-36.pyc b/q02_Max_important_feature/tests/__pycache__/test_q02max_important_feature.cpython-36.pyc index cb6849b..d948764 100644 Binary files a/q02_Max_important_feature/tests/__pycache__/test_q02max_important_feature.cpython-36.pyc and b/q02_Max_important_feature/tests/__pycache__/test_q02max_important_feature.cpython-36.pyc differ diff --git a/q03_polynomial/__pycache__/__init__.cpython-36.pyc b/q03_polynomial/__pycache__/__init__.cpython-36.pyc index aa42922..3057c5e 100644 Binary files a/q03_polynomial/__pycache__/__init__.cpython-36.pyc and b/q03_polynomial/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_polynomial/__pycache__/build.cpython-36.pyc b/q03_polynomial/__pycache__/build.cpython-36.pyc index 3be41d0..14d2f20 100644 Binary files a/q03_polynomial/__pycache__/build.cpython-36.pyc and b/q03_polynomial/__pycache__/build.cpython-36.pyc differ diff --git a/q03_polynomial/build.py b/q03_polynomial/build.py index 26d8971..b1d3371 100644 --- a/q03_polynomial/build.py +++ b/q03_polynomial/build.py @@ -1,11 +1,24 @@ +# %load q03_polynomial/build.py # Default imports from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data from sklearn.preprocessing import PolynomialFeatures from sklearn.pipeline import make_pipeline from sklearn.linear_model import LinearRegression + # We have already loaded the data for you data_set, X_train, X_test, y_train, y_test = load_data('data/house_prices_multivariate.csv') - +X_train = X_train[['OverallQual','GrLivArea','GarageCars','GarageArea']] +X_test = X_test[['OverallQual','GrLivArea','GarageCars','GarageArea']] # Write your solution here +def polynomial(power=5,Random_state=9): + # PolynomialFeatures (prepreprocessing) + poly_model = make_pipeline(PolynomialFeatures(power,include_bias=False), + LinearRegression()) + poly_model.fit(X_train,y_train) + return poly_model + +polynomial(power=5,Random_state=9) + + diff --git a/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc b/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc index 6e20876..a1dc0bc 100644 Binary files a/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc and b/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_polynomial/tests/__pycache__/test_q03_polynomial.cpython-36.pyc b/q03_polynomial/tests/__pycache__/test_q03_polynomial.cpython-36.pyc index ef8c88b..fa7a680 100644 Binary files a/q03_polynomial/tests/__pycache__/test_q03_polynomial.cpython-36.pyc and b/q03_polynomial/tests/__pycache__/test_q03_polynomial.cpython-36.pyc differ diff --git a/q04_ridge/__pycache__/__init__.cpython-36.pyc b/q04_ridge/__pycache__/__init__.cpython-36.pyc index 4342136..dbe6024 100644 Binary files a/q04_ridge/__pycache__/__init__.cpython-36.pyc and b/q04_ridge/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_ridge/__pycache__/build.cpython-36.pyc b/q04_ridge/__pycache__/build.cpython-36.pyc index ea08c01..b4fb824 100644 Binary files a/q04_ridge/__pycache__/build.cpython-36.pyc and b/q04_ridge/__pycache__/build.cpython-36.pyc differ diff --git a/q04_ridge/build.py b/q04_ridge/build.py index 9ee00b1..9bbba23 100644 --- a/q04_ridge/build.py +++ b/q04_ridge/build.py @@ -1,15 +1,27 @@ +# %load q04_ridge/build.py # Default imports from sklearn.linear_model import Ridge import pandas as pd import numpy as np from sklearn.metrics import mean_squared_error from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data -np.random.seed(9) # We have already loaded the data for you data_set, X_train, X_test, y_train, y_test = load_data('data/house_prices_multivariate.csv') +np.random.seed(9) + # Write your solution here +def ridge(alpha = 0.01): + model = Ridge(alpha, normalize= True,random_state=9) + Regressor = model.fit(X_train, y_train) + y_train_pred = Regressor.predict(X_train) + y_test_pred = Regressor.predict(X_test) + RMSE_TRAIN = (mean_squared_error(y_train_pred, y_train))**0.5 + RMSE_TEST = (mean_squared_error(y_test_pred, y_test))**0.5 + return RMSE_TRAIN,RMSE_TEST,model + + diff --git a/q04_ridge/tests/__pycache__/__init__.cpython-36.pyc b/q04_ridge/tests/__pycache__/__init__.cpython-36.pyc index 6d021b5..84e785a 100644 Binary files a/q04_ridge/tests/__pycache__/__init__.cpython-36.pyc and b/q04_ridge/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q04_ridge/tests/__pycache__/test_q04_ridge.cpython-36.pyc b/q04_ridge/tests/__pycache__/test_q04_ridge.cpython-36.pyc index 0549421..a4dd054 100644 Binary files a/q04_ridge/tests/__pycache__/test_q04_ridge.cpython-36.pyc and b/q04_ridge/tests/__pycache__/test_q04_ridge.cpython-36.pyc differ diff --git a/q05_lasso/__pycache__/__init__.cpython-36.pyc b/q05_lasso/__pycache__/__init__.cpython-36.pyc index 1005306..46c4a00 100644 Binary files a/q05_lasso/__pycache__/__init__.cpython-36.pyc and b/q05_lasso/__pycache__/__init__.cpython-36.pyc differ diff --git a/q05_lasso/__pycache__/build.cpython-36.pyc b/q05_lasso/__pycache__/build.cpython-36.pyc index b4ea629..6cddd9f 100644 Binary files a/q05_lasso/__pycache__/build.cpython-36.pyc and b/q05_lasso/__pycache__/build.cpython-36.pyc differ diff --git a/q05_lasso/build.py b/q05_lasso/build.py index fb30d50..937b2f4 100644 --- a/q05_lasso/build.py +++ b/q05_lasso/build.py @@ -1,14 +1,26 @@ +# %load q05_lasso/build.py # Default imports from sklearn.linear_model import Lasso import pandas as pd import numpy as np from sklearn.metrics import mean_squared_error from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data -np.random.seed(9) # We have already loaded the data for you data_set, X_train, X_test, y_train, y_test = load_data('data/house_prices_multivariate.csv') +np.random.seed(9) + # Write your solution here +def lasso(alpha = 0.01): + model = Lasso(alpha, normalize= True,random_state=9) + Regressor = model.fit(X_train, y_train) + y_train_pred = Regressor.predict(X_train) + y_test_pred = Regressor.predict(X_test) + RMSE_TRAIN = (mean_squared_error(y_train_pred, y_train))**0.5 + RMSE_TEST = (mean_squared_error(y_test_pred, y_test))**0.5 + return RMSE_TRAIN,RMSE_TEST + + diff --git a/q05_lasso/tests/__pycache__/__init__.cpython-36.pyc b/q05_lasso/tests/__pycache__/__init__.cpython-36.pyc index 8869434..6ac6a13 100644 Binary files a/q05_lasso/tests/__pycache__/__init__.cpython-36.pyc and b/q05_lasso/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q05_lasso/tests/__pycache__/test_q05_lasso.cpython-36.pyc b/q05_lasso/tests/__pycache__/test_q05_lasso.cpython-36.pyc index 438235e..35616a4 100644 Binary files a/q05_lasso/tests/__pycache__/test_q05_lasso.cpython-36.pyc and b/q05_lasso/tests/__pycache__/test_q05_lasso.cpython-36.pyc differ diff --git a/q06_cross_validation/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/__pycache__/__init__.cpython-36.pyc index fa7d8bf..45fbc25 100644 Binary files a/q06_cross_validation/__pycache__/__init__.cpython-36.pyc and b/q06_cross_validation/__pycache__/__init__.cpython-36.pyc differ diff --git a/q06_cross_validation/__pycache__/build.cpython-36.pyc b/q06_cross_validation/__pycache__/build.cpython-36.pyc index 19e8bd8..970d1e8 100644 Binary files a/q06_cross_validation/__pycache__/build.cpython-36.pyc and b/q06_cross_validation/__pycache__/build.cpython-36.pyc differ diff --git a/q06_cross_validation/build.py b/q06_cross_validation/build.py index e39b93b..a127722 100644 --- a/q06_cross_validation/build.py +++ b/q06_cross_validation/build.py @@ -1,13 +1,19 @@ +# %load q06_cross_validation/build.py # Default imports from sklearn.model_selection import cross_val_score import numpy as np from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data +from sklearn.linear_model import Ridge -np.random.seed(9) # We have already loaded the data for you data_set, X_train, X_test, y_train, y_test = load_data('data/house_prices_multivariate.csv') - +np.random.seed(9) # Write your solution here +def cross_validation(model, X,y): + model.fit(X_train,y_train) + scores = cross_val_score(model, X, y, scoring='neg_mean_squared_error', cv=5) + return scores.mean() + diff --git a/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc index ca3f5cd..c76ef5a 100644 Binary files a/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc and b/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q06_cross_validation/tests/__pycache__/test_q06_cross_validation.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/test_q06_cross_validation.cpython-36.pyc index e7acaaf..732aaeb 100644 Binary files a/q06_cross_validation/tests/__pycache__/test_q06_cross_validation.cpython-36.pyc and b/q06_cross_validation/tests/__pycache__/test_q06_cross_validation.cpython-36.pyc differ