diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index ebbd53a..66b3dd0 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..520970d 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..c990e18 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..eb79fbe 100644 --- a/q01_load_data/build.py +++ b/q01_load_data/build.py @@ -1,10 +1,18 @@ +# %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,index_col=0) + Y=df.iloc[:,33] + x=df.iloc[:,:34] + X_train, X_test, y_train, y_test = train_test_split(x,Y,test_size=test_size, random_state=Random_state) + return df,X_train, X_test, y_train, y_test +dff,X_train, X_test, y_train, y_test = load_data(path='data/house_prices_multivariate.csv') +X_train.shape -# Write your solution here diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc index 133357e..0b930be 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..9284f9b 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..587b842 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..a5caefa 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..9c565d8 100644 --- a/q02_Max_important_feature/build.py +++ b/q02_Max_important_feature/build.py @@ -1,3 +1,4 @@ +# %load q02_Max_important_feature/build.py # Default imports from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data @@ -6,3 +7,10 @@ # Write your code here +def Max_important_feature(data_set,target_variable='SalePrice',n=4): + col=len(data_set.columns)-1 + return data_set.iloc[:,:col].apply(lambda x: x.corr(data_set.loc[:,target_variable])).abs().sort_values(ascending = False).head(n).index + +Max_important_feature(data_set,'SalePrice',4) + + 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..0a788c8 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..6a2ca57 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..e5a45bf 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..4e8c1c4 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..14c343c 100644 --- a/q03_polynomial/build.py +++ b/q03_polynomial/build.py @@ -1,3 +1,4 @@ +# %load q03_polynomial/build.py # Default imports from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data from sklearn.preprocessing import PolynomialFeatures @@ -9,3 +10,9 @@ # Write your solution here +def polynomial(power=5,Random_state=9): + return make_pipeline(PolynomialFeatures(power,include_bias=False),LinearRegression()).fit(X_train[['OverallQual','GrLivArea','GarageCars','GarageArea']],y_train) + +polynomial(5,9) + + diff --git a/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc b/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc index 6e20876..762b3a3 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..b1590dd 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..3e392d1 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..9005168 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..a9de150 100644 --- a/q04_ridge/build.py +++ b/q04_ridge/build.py @@ -1,15 +1,23 @@ +# %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=alpha, normalize=True, random_state=9) + model.fit(X_train, y_train) + return np.sqrt(mean_squared_error(model.predict(X_train), y_train)), np.sqrt(mean_squared_error(model.predict(X_test), y_test)), model + +ridge() + diff --git a/q04_ridge/tests/__pycache__/__init__.cpython-36.pyc b/q04_ridge/tests/__pycache__/__init__.cpython-36.pyc index 6d021b5..609af4f 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..98639ba 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..5bdd554 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..6e767ad 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..16e9c40 100644 --- a/q05_lasso/build.py +++ b/q05_lasso/build.py @@ -1,14 +1,30 @@ +# %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=alpha,normalize=True,random_state=9) + model.fit(X_train,y_train) + + y_pred_train=model.predict(X_train) + y_pred_test=model.predict(X_test) + + m1=mean_squared_error(y_train,y_pred_train) + m2=mean_squared_error(y_test,y_pred_test) + + return np.sqrt(m1), np.sqrt(m2) + + +lasso() + diff --git a/q05_lasso/tests/__pycache__/__init__.cpython-36.pyc b/q05_lasso/tests/__pycache__/__init__.cpython-36.pyc index 8869434..933308c 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..76186d3 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..4f56e8c 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..6e744ae 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..c1d51c7 100644 --- a/q06_cross_validation/build.py +++ b/q06_cross_validation/build.py @@ -1,13 +1,22 @@ +# %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) + +model = Ridge(alpha=0.01) # Write your solution here +def cross_validation(Model, X, y): + scores = cross_val_score(Model, X, y, scoring='neg_mean_squared_error', cv=5) + return scores.mean() + +cross_validation(model,X_train,y_train) diff --git a/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/__init__.cpython-36.pyc index ca3f5cd..b3a5729 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..51d26c9 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