commit-live-students · Tusharshah2006 · Nov 29, 2018 · Nov 29, 2018 · Nov 29, 2018 · Dec 1, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/__pycache__/__init__.cpython-36.pyc b/q01_load_data/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/__pycache__/build.cpython-36.pyc b/q01_load_data/__pycache__/build.cpython-36.pyc
diff --git a/q01_load_data/build.py b/q01_load_data/build.py
@@ -1,4 +1,12 @@
+# %load q01_load_data/build.py
 import pandas as pd
+path = './data/student-mat.csv'
 
 # Write your code below
-
+def load_data(path):
+    df = pd.read_table(path, sep=';')
+    return df
+
+df = load_data(path)
+
+
diff --git a/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc b/q01_load_data/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_load_data/tests/__pycache__/test.cpython-36.pyc b/q01_load_data/tests/__pycache__/test.cpython-36.pyc
diff --git a/q02_data_split/__pycache__/__init__.cpython-36.pyc b/q02_data_split/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_data_split/__pycache__/build.cpython-36.pyc b/q02_data_split/__pycache__/build.cpython-36.pyc
diff --git a/q02_data_split/build.py b/q02_data_split/build.py
@@ -1,8 +1,17 @@
+# %load q02_data_split/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from sklearn.model_selection import train_test_split
 import pandas as pd
 df = load_data('data/student-mat.csv')
 
 # Write your code below
+def split_dataset(df):
+    X = df.drop(['G3'], 1)
+    y = df['G3']
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state = 42)
 
+    return X_train, X_test, y_train, y_test
 
+X_train, X_test, y_train, y_test = split_dataset(df)
+
+
diff --git a/q02_data_split/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_split/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_data_split/tests/__pycache__/test.cpython-36.pyc b/q02_data_split/tests/__pycache__/test.cpython-36.pyc
diff --git a/q03_data_encoding/__pycache__/__init__.cpython-36.pyc b/q03_data_encoding/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_data_encoding/__pycache__/build.cpython-36.pyc b/q03_data_encoding/__pycache__/build.cpython-36.pyc
diff --git a/q03_data_encoding/build.py b/q03_data_encoding/build.py
@@ -1,3 +1,4 @@
+# %load q03_data_encoding/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from sklearn.preprocessing import LabelEncoder
@@ -8,7 +9,13 @@
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
 # Write your code below
+def label_encode(X_train, X_test):
+    lblEncd = LabelEncoder()
+    X_transform = x_train.apply(lblEncd.fit_transform)
+    X_test_transform = x_test.apply(lblEncd.fit_transform)
 
-
+    return X_transform, X_test_transform 
+
+X_transform, X_test_transform = label_encode(x_train, x_test)
 
 
diff --git a/q03_data_encoding/tests/__pycache__/__init__.cpython-36.pyc b/q03_data_encoding/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_data_encoding/tests/__pycache__/test.cpython-36.pyc b/q03_data_encoding/tests/__pycache__/test.cpython-36.pyc
diff --git a/q03_ohe_encoder/__pycache__/__init__.cpython-36.pyc b/q03_ohe_encoder/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_ohe_encoder/__pycache__/build.cpython-36.pyc b/q03_ohe_encoder/__pycache__/build.cpython-36.pyc
diff --git a/q03_ohe_encoder/build.py b/q03_ohe_encoder/build.py
@@ -1,6 +1,8 @@
+# %load q03_ohe_encoder/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from sklearn.preprocessing import OneHotEncoder
+from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
 import pandas as pd
 import numpy as np
 
@@ -10,10 +12,15 @@
 
 category_index = [x for x in range(len(df.columns)) if df[df.columns[x]].dtype == 'object']
 
-
 # Write your code below
-
+def ohe_encode(x_train, x_test, category_index=category_index):
+    x_train,x_test = label_encode(x_train,x_test)
+    oneHotEncd = OneHotEncoder(categorical_features=category_index, sparse=False)
+    X_transform = oneHotEncd.fit_transform(x_train)
+    X_test_transform = oneHotEncd.fit_transform(x_test)
 
-
+    return X_transform, X_test_transform
 
-
+X_transform, X_test_transform = ohe_encode(x_train, x_test)
+
+
diff --git a/q03_ohe_encoder/tests/__pycache__/__init__.cpython-36.pyc b/q03_ohe_encoder/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_ohe_encoder/tests/__pycache__/test.cpython-36.pyc b/q03_ohe_encoder/tests/__pycache__/test.cpython-36.pyc
diff --git a/q04_data_visualisation/__pycache__/__init__.cpython-36.pyc b/q04_data_visualisation/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_data_visualisation/__pycache__/build.cpython-36.pyc b/q04_data_visualisation/__pycache__/build.cpython-36.pyc
diff --git a/q04_data_visualisation/build.py b/q04_data_visualisation/build.py
@@ -1,16 +1,17 @@
-# -*- coding: utf-8 -*-
+# %load q04_data_visualisation/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
 
 import matplotlib.pyplot as plt
 from pandas.plotting import scatter_matrix
-data = load_data('data/student-mat.csv') 
+data = load_data('data/student-mat.csv')
 x_train, x_test, y_train, y_test =  split_dataset(data)
 x_train,x_test = label_encode(x_train,x_test)
 
 # Write your code below
-
-
-
+def visualise_data(data, figname):
+    return scatter_matrix(data)
+
+
 
diff --git a/q04_data_visualisation/tests/__pycache__/__init__.cpython-36.pyc b/q04_data_visualisation/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_data_visualisation/tests/__pycache__/test.cpython-36.pyc b/q04_data_visualisation/tests/__pycache__/test.cpython-36.pyc
diff --git a/q05_linear_regression_model/__pycache__/__init__.cpython-36.pyc b/q05_linear_regression_model/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_linear_regression_model/__pycache__/build.cpython-36.pyc b/q05_linear_regression_model/__pycache__/build.cpython-36.pyc
diff --git a/q05_linear_regression_model/build.py b/q05_linear_regression_model/build.py
@@ -1,3 +1,4 @@
+# %load q05_linear_regression_model/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
@@ -12,4 +13,12 @@
 
 
 # Write your code below
+def linear_regression(X, y):
+    lr = LinearRegression()
+    lm = lr.fit(X, y)
 
+    return lm
+
+linear_regression(x_train, y_train)
+
+
diff --git a/q05_linear_regression_model/tests/__pycache__/__init__.cpython-36.pyc b/q05_linear_regression_model/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q05_linear_regression_model/tests/__pycache__/test.cpython-36.pyc b/q05_linear_regression_model/tests/__pycache__/test.cpython-36.pyc
diff --git a/q06_cross_validation/__pycache__/__init__.cpython-36.pyc b/q06_cross_validation/__pycache__/__init__.cpython-36.pyc
diff --git a/q06_cross_validation/__pycache__/build.cpython-36.pyc b/q06_cross_validation/__pycache__/build.cpython-36.pyc
diff --git a/q06_cross_validation/build.py b/q06_cross_validation/build.py
@@ -1,3 +1,4 @@
+# %load q06_cross_validation/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
@@ -18,4 +19,10 @@
 model =linear_regression(x_train,y_train)
 
 # Write your code below
+def cross_validation_regressor(Model, X, y):
+    r2_score = np.array(cross_val_score(Model, X, y, cv=3)).mean()
+    return r2_score
 
+cross_validation_regressor(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
diff --git a/q06_cross_validation/tests/__pycache__/test.cpython-36.pyc b/q06_cross_validation/tests/__pycache__/test.cpython-36.pyc
diff --git a/q07_regression_pred/__pycache__/__init__.cpython-36.pyc b/q07_regression_pred/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_regression_pred/__pycache__/build.cpython-36.pyc b/q07_regression_pred/__pycache__/build.cpython-36.pyc
diff --git a/q07_regression_pred/build.py b/q07_regression_pred/build.py
@@ -1,3 +1,4 @@
+# %load q07_regression_pred/build.py
 
 from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
 
@@ -10,13 +11,25 @@
 
 df = load_data('data/student-mat.csv')
 
-x_train, x_test, y_train, y_test =  split_dataset(df)
+x_train, x_test, y_train, y_test = split_dataset(df)
 
 x_train,x_test = label_encode(x_train,x_test)
 
 model =linear_regression(x_train,y_train)
 
 val = cross_validation_regressor(model,x_train,y_train)
 
-
 # Write your code below    
+def regression_predictor(model,X,y):
+    y_pred = model.predict(X)
+    mse = mean_squared_error(y,y_pred)
+    mae = mean_absolute_error(y,y_pred)
+    r2 = r2_score(y,y_pred)
+
+    return y_pred, mse, mae, r2
+
+regression_predictor(model, x_test, y_test)
+
+
+
+
diff --git a/q07_regression_pred/tests/__pycache__/__init__.cpython-36.pyc b/q07_regression_pred/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q07_regression_pred/tests/__pycache__/test.cpython-36.pyc b/q07_regression_pred/tests/__pycache__/test.cpython-36.pyc
diff --git a/q08_linear_model/__pycache__/__init__.cpython-36.pyc b/q08_linear_model/__pycache__/__init__.cpython-36.pyc
diff --git a/q08_linear_model/__pycache__/build.cpython-36.pyc b/q08_linear_model/__pycache__/build.cpython-36.pyc
diff --git a/q08_linear_model/build.py b/q08_linear_model/build.py
@@ -1,3 +1,4 @@
+# %load q08_linear_model/build.py
 import pandas as pd
 import numpy as np
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
@@ -16,5 +17,12 @@
 y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
 
 # Write your code below
+def linear_model(x_train, x_test, y_train, y_test):
+    G = linear_regression(x_train, y_train)
+    stats = pd.DataFrame([(val,mae,mse,r2)], columns = ['cross_val','rmse','mae','r2'])
 
+    return G, y_pred, stats
 
+linear_model(x_train, x_test, y_train, y_test)
+
+
diff --git a/q08_linear_model/tests/__pycache__/__init__.cpython-36.pyc b/q08_linear_model/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q08_linear_model/tests/__pycache__/test.cpython-36.pyc b/q08_linear_model/tests/__pycache__/test.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q01_lasso/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/__pycache__/build.cpython-36.pyc b/q09_advanced_model_q01_lasso/__pycache__/build.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/build.py b/q09_advanced_model_q01_lasso/build.py
@@ -1,3 +1,4 @@
+# %load q09_advanced_model_q01_lasso/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
@@ -19,5 +20,16 @@
 x_train,x_test = label_encode(x_train,x_test)
 
 # Write your solution here
+def lasso(x_train, x_test, y_train, y_test, alpha=0.1):
+    G = Lasso(alpha = alpha)
+    G.fit(x_train, y_train)
+    val = cross_validation_regressor(G,x_train,y_train)
+    y_pred, mse, mae, r2 = regression_predictor(G, x_test, y_test)
+
+    stats = pd.DataFrame([(val,mae,r2,np.sqrt(mse))], columns = ['cross_val','mae','r2','rmse'])
 
+    return G, y_pred, stats
 
+lasso(x_train, x_test, y_train, y_test)
+
+
diff --git a/q09_advanced_model_q01_lasso/tests/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q01_lasso/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q01_lasso/tests/__pycache__/test.cpython-36.pyc b/q09_advanced_model_q01_lasso/tests/__pycache__/test.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q02_ridge/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/__pycache__/build.cpython-36.pyc b/q09_advanced_model_q02_ridge/__pycache__/build.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/build.py b/q09_advanced_model_q02_ridge/build.py
@@ -1,3 +1,4 @@
+# %load q09_advanced_model_q02_ridge/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
@@ -19,7 +20,16 @@
 x_train,x_test = label_encode(x_train,x_test)
 
 # Write your code below
-
+def ridge(x_train, x_test, y_train, y_test, alpha=0.1):
+    G = Ridge(alpha = alpha,normalize = True)
+    G.fit(x_train, y_train)
+    val = cross_validation_regressor(G,x_train,y_train)
+    y_pred, mse, mae, r2 = regression_predictor(G, x_test, y_test)
+
+    stats = pd.DataFrame([(val,mae,r2,np.sqrt(mse))], columns = ['cross_val','mae','r2','rmse'])
 
+    return G, y_pred, stats
 
+ridge(x_train, x_test, y_train, y_test)
+
 
diff --git a/q09_advanced_model_q02_ridge/tests/__pycache__/__init__.cpython-36.pyc b/q09_advanced_model_q02_ridge/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q09_advanced_model_q02_ridge/tests/__pycache__/test.cpython-36.pyc b/q09_advanced_model_q02_ridge/tests/__pycache__/test.cpython-36.pyc
diff --git a/q10_data_missing_values/__pycache__/__init__.cpython-36.pyc b/q10_data_missing_values/__pycache__/__init__.cpython-36.pyc
diff --git a/q10_data_missing_values/__pycache__/build.cpython-36.pyc b/q10_data_missing_values/__pycache__/build.cpython-36.pyc
diff --git a/q10_data_missing_values/build.py b/q10_data_missing_values/build.py
@@ -1,3 +1,4 @@
+# %load q10_data_missing_values/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
@@ -10,4 +11,12 @@
 x_train,x_test = label_encode(x_train,x_test)
 
 # Write your code below
+def describe_df(x_train):  
+    describe = x_train.describe()
+    value_counts = x_train.apply(pd.value_counts)
 
+    return describe, value_counts
+
+describe_df(x_train)
+
+
diff --git a/q10_data_missing_values/tests/__pycache__/__init__.cpython-36.pyc b/q10_data_missing_values/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q10_data_missing_values/tests/__pycache__/test.cpython-36.pyc b/q10_data_missing_values/tests/__pycache__/test.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/__pycache__/build.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/build.py b/q11_feature_selection_q01_plot_corr/build.py
@@ -1,13 +1,12 @@
-
+# %load q11_feature_selection_q01_plot_corr/build.py
+import matplotlib
+matplotlib.use('agg')
 import matplotlib.pyplot as plt
 from matplotlib.pyplot import yticks, xticks, subplots, set_cmap
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 
-
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
-
-
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
 
 df = load_data('data/student-mat.csv')
@@ -21,6 +20,19 @@
 
 #Remember to concatenate training features and labels if you want to check that scatterplots which I would prefer.You are free to explore labels to labels, features to features ,etc scatterplots as you want by passing arguments
 #============================================================================
-#visualise_data(pd.concat([x_train,y_train],axis=1),"../images/data_image.png")
+#visualise_data(pd.concat([x_train,y_train],axis=1),'../images/data_image.png')
 
 # Write your solution here:
+def plot_corr(df, size=11):
+    fig, axis = plt.subplots(figsize=(size, size))
+    cor = df.corr()
+    plt.set_cmap(cmap='YlOrRd')
+    axis.matshow(cor)
+
+    plt.xticks(range(len(cor.columns)), cor.columns, rotation=90);
+    plt.yticks(range(len(cor.columns)), cor.columns);
+    plt.show()
+
+plot_corr(df)
+
+
diff --git a/q11_feature_selection_q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q01_plot_corr/tests/__pycache__/test.cpython-36.pyc b/q11_feature_selection_q01_plot_corr/tests/__pycache__/test.cpython-36.pyc
diff --git a/q11_feature_selection_q02_best_k_features/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q02_best_k_features/__pycache__/build.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/__pycache__/build.cpython-36.pyc
diff --git a/q11_feature_selection_q02_best_k_features/build.py b/q11_feature_selection_q02_best_k_features/build.py
@@ -1,8 +1,10 @@
+# %load q11_feature_selection_q02_best_k_features/build.py
 # Default imports
 from sklearn.feature_selection import SelectPercentile
 from sklearn.feature_selection import f_regression
 import numpy as np
 import matplotlib.pyplot as plt
+import operator
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
@@ -17,11 +19,26 @@
 
 x_train,x_test = label_encode(x_train,x_test)
 
-
 np.random.seed(9)
 # Write your code below
+def percentile_k_features(x_train, y_train, k=50):
+    Selector_f = SelectPercentile(f_regression, percentile=k)
+    fs = Selector_f.fit(x_train, y_train)
+    cols = list(x_train.columns)
+    scores = list(fs.scores_)
+
+    feature_score = dict()
+    top_k_predictors = []
+    for i in range(0,len(cols)):
+        feature_score[cols[i]] = scores[i]
 
+    sorted_x = sorted(feature_score.items(), key=operator.itemgetter(1), reverse=True)
+    for obj in range(0, 16):
+        top_k_predictors.append(sorted_x[obj][0])
 
+    return top_k_predictors
+
+percentile_k_features(x_train, y_train)
 
 
 
diff --git a/q11_feature_selection_q02_best_k_features/tests/__pycache__/__init__.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q11_feature_selection_q02_best_k_features/tests/__pycache__/test.cpython-36.pyc b/q11_feature_selection_q02_best_k_features/tests/__pycache__/test.cpython-36.pyc
diff --git a/q12_feature_selection/__pycache__/__init__.cpython-36.pyc b/q12_feature_selection/__pycache__/__init__.cpython-36.pyc
diff --git a/q12_feature_selection/__pycache__/build.cpython-36.pyc b/q12_feature_selection/__pycache__/build.cpython-36.pyc
diff --git a/q12_feature_selection/build.py b/q12_feature_selection/build.py
@@ -1,3 +1,4 @@
+# %load q12_feature_selection/build.py
 # import matplotlib.pyplot as plt
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
@@ -16,3 +17,12 @@
 x_train,x_test = label_encode(x_train,x_test)
 
 # Write your code below
+def feature_selection(x_train, y_train, k=50):
+    plot_corr(pd.concat([x_train, y_train],axis=1))
+    reduced_features = percentile_k_features(x_train,y_train,k)
+
+    return reduced_features
+
+feature_selection(x_train, y_train)
+
+
diff --git a/q12_feature_selection/tests/__pycache__/__init__.cpython-36.pyc b/q12_feature_selection/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q12_feature_selection/tests/__pycache__/test.cpython-36.pyc b/q12_feature_selection/tests/__pycache__/test.cpython-36.pyc
diff --git a/q13_plot_residuals/__pycache__/__init__.cpython-36.pyc b/q13_plot_residuals/__pycache__/__init__.cpython-36.pyc
diff --git a/q13_plot_residuals/__pycache__/build.cpython-36.pyc b/q13_plot_residuals/__pycache__/build.cpython-36.pyc
diff --git a/q13_plot_residuals/build.py b/q13_plot_residuals/build.py
@@ -1,5 +1,11 @@
-
-
+# %load q13_plot_residuals/build.py
+import matplotlib
+matplotlib.use('Agg')
 import matplotlib.pyplot as plt
 
 # Write your code below
+def plot_residuals(y_test, y_pred, name):
+    plt.plot(y_test, y_pred)
+    plt.show()
+
+
diff --git a/q13_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc b/q13_plot_residuals/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q13_plot_residuals/tests/__pycache__/test.cpython-36.pyc b/q13_plot_residuals/tests/__pycache__/test.cpython-36.pyc
diff --git a/q14_benchmarking/__pycache__/__init__.cpython-36.pyc b/q14_benchmarking/__pycache__/__init__.cpython-36.pyc
diff --git a/q14_benchmarking/__pycache__/build.cpython-36.pyc b/q14_benchmarking/__pycache__/build.cpython-36.pyc
diff --git a/q14_benchmarking/build.py b/q14_benchmarking/build.py
@@ -1,3 +1,4 @@
+# %load q14_benchmarking/build.py
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
@@ -26,5 +27,22 @@
 
 
 # Write your code below
+def create_stats(x_train, x_test, y_train, y_test):
+    lasso_modl, lasso_y_pred, lasso_stat = lasso(x_train, x_test, y_train, y_test,0.1)
+    ridge_modl, ridge_y_pred, ridge_stat = ridge(x_train, x_test, y_train, y_test,0.1)
+    features = feature_selection(x_train, y_train, k=50)
+
+    x_train_ft = x_train[features].copy()
+    x_test_ft = x_test[features].copy()
+
+    lasso_modl_ft, lasso_y_pred_ft, lasso_stat_ft = lasso(x_train_ft, x_test_ft, y_train, y_test,0.1)
+    ridge_modl_ft, ridge_y_pred_ft, ridge_stat_ft = ridge(x_train_ft, x_test_ft, y_train, y_test,0.1)
+    features = feature_selection(x_train_ft, y_train, k=50)
+
+    complete_stats = pd.concat([lasso_stat,lasso_stat_ft,ridge_stat,ridge_stat_ft])
+
+    return complete_stats
+
+create_stats(x_train, x_test, y_train, y_test)
 
 
diff --git a/q14_benchmarking/tests/__pycache__/__init__.cpython-36.pyc b/q14_benchmarking/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q14_benchmarking/tests/__pycache__/test.cpython-36.pyc b/q14_benchmarking/tests/__pycache__/test.cpython-36.pyc