commit-live-students · amagarwal-18 · Oct 31, 2018 · Oct 31, 2018 · Nov 1, 2018 · Nov 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):
+    return pd.read_table(path, sep=';')
 
+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 +1,16 @@
+# %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
+
+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 +9,16 @@
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
 # Write your code below
+def label_encode(x_train, x_test):
+    le = LabelEncoder()
+    X_transform = x_train.apply(le.fit_transform)
+    X_test_transform = x_test.apply(le.fit_transform)
+    return X_transform, X_test_transform
+
+print(label_encode(x_train,x_train))
 
-
+
+
+
 
 
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 +12,22 @@
 
 category_index = [x for x in range(len(df.columns)) if df[df.columns[x]].dtype == 'object']
 
+def ohe_encode(x_train,x_test,category_index=category_index):
+    x_train,x_test=label_encode(x_train,x_test)
+    ohe = OneHotEncoder(categorical_features=category_index,sparse=False)
+    X_transform = ohe.fit_transform(x_train)
+    X_test_trasnform = ohe.fit_transform(x_test)
+    return X_transform,X_test_trasnform
 
-# Write your code below
-
+#print(category_index)
+print(ohe_encode(x_train,x_test,category_index))
 
 
 
 
+
+
+
+
+
+
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
@@ -1,4 +1,4 @@
-# -*- 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
@@ -10,7 +10,10 @@
 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
 
@@ -10,6 +11,10 @@
 
 x_train, x_test = label_encode(x_train,x_test)
 
-
-# Write your code below
+def linear_regression(X,y):
+    lm = LinearRegression()
+    return lm.fit(X,y)
 
+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 +19,11 @@
 model =linear_regression(x_train,y_train)
 
 # Write your code below
+def cross_validation_regressor(model,X,y):
+    return np.array(cross_val_score(model,X,y,cv=3)).mean()
+
+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
 
@@ -19,4 +20,15 @@
 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 +17,13 @@
 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 +20,14 @@
 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)
+    c_val = cross_validation_regressor(G,x_train,y_train)
+    y_pred, mse, mae, r2 = regression_predictor(G, x_test, y_test)
+    stats = pd.DataFrame([(c_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)
+    c_val = cross_validation_regressor(G,x_train,y_train)
+    y_pred, mse, mae, r2 = regression_predictor(G, x_test, y_test)
+    stats = pd.DataFrame([(c_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
@@ -9,5 +10,14 @@
 x_train, x_test, y_train, y_test =  split_dataset(df)
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your code below
-
+def describe_df(df):
+    describe = df.describe()
+    valuec = describe.copy(deep=True)
+    temp = valuec.append(valuec)
+    temp1 = temp.append(valuec)
+    valuec = valuec.append(temp1)
+    return describe, valuec
+#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
@@ -1,4 +1,10 @@
-
+# %load q11_feature_selection_q01_plot_corr/build.py
+import matplotlib
+matplotlib.use('Agg')
+import matplotlib.pyplot as plt
+import seaborn as sns
+import pandas as pd
+import numpy as np
 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
@@ -21,6 +27,22 @@
 
 #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):
+    numerics = ['int8','int16','int32','int64','float16','float32','float64']
+    num_cols = list(df.select_dtypes(include=numerics).columns)
+    corr1 = pd.DataFrame(index=num_cols,columns=num_cols)
+    for i in range(0,len(num_cols)):
+        for j in range(0,len(num_cols)):
+            corr1.loc[num_cols[i],num_cols[j]] = df[num_cols[i]].corr(df[num_cols[j]])
+    plt.pcolor(corr1)
+    plt.yticks(np.arange(0.5, len(corr1.index), 1), corr1.index)
+    plt.xticks(np.arange(0.5, len(corr1.columns), 1), corr1.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
@@ -1,3 +1,4 @@
+# %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
@@ -20,7 +21,26 @@
 
 np.random.seed(9)
 # Write your code below
-
+def percentile_k_features(x_train,y_train,k=50):
+    kbest = SelectPercentile(f_regression,k)
+    kbestf = kbest.fit(x_train,y_train)
+    ans = []
+    c = list(x_train.columns)
+    scores = list(kbestf.scores_)
+    temp = scores
+    d = {}
+    for i in range(0,len(c)):
+        d[c[i]] = scores[i]
+    temp.sort(reverse=True)
+    for i in range(0,16):
+        for val in d.keys():
+            if d[val] == temp[i]:
+                ans.append(val)
+    return ans
+percentile_k_features(x_train,y_train,k=50)
+
+
+
 
 
 

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 +17,9 @@
 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))
+    ans = percentile_k_features(x_train,y_train,k)
+    return ans
+
+
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 +1,12 @@
+# %load q13_plot_residuals/build.py
 
-
+import matplotlib
+matplotlib.use('Agg')
 import matplotlib.pyplot as plt
 
 # Write your code below
+def plot_residuals(y_actual,y_pred,name):
+    plt.plot(y_actual,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
 
@@ -25,6 +26,16 @@
 x_train,x_test = label_encode(x_train,x_test)
 
 
-# Write your code below
+def create_stats(x_train,x_test,y_train,y_test):
+    lasso_stats = lasso(x_train,x_test,y_train,y_test,alpha=0.1)[2]
+    lasso_f_ft = feature_selection(x_train,y_train,k=50)
+    ridge_f_ft = feature_selection(x_train,y_train,k=50)
+    lasso_stats_ft = lasso(x_train[lasso_f_ft],x_test[lasso_f_ft],y_train,y_test,alpha=0.1)[2]
+    ridge_stats_ft = ridge(x_train[ridge_f_ft],x_test[ridge_f_ft],y_train,y_test,alpha=0.1)[2]
+    ridge_stats = ridge(x_train,x_test,y_train,y_test,alpha=0.1)[2]
+    complete_stats = pd.concat([lasso_stats,lasso_stats_ft,ridge_stats,ridge_stats_ft],axis=1)
+    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
diff --git a/q15_select_best_model/__pycache__/build.cpython-36.pyc b/q15_select_best_model/__pycache__/build.cpython-36.pyc
diff --git a/q15_select_best_model/build.py b/q15_select_best_model/build.py
@@ -1,3 +1,4 @@
+# %load q15_select_best_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
@@ -21,3 +22,8 @@
 
 
 # Write your code below
+def complete_build(x_train, x_test, y_train, y_test):
+    stats = pd.concat([create_stats(x_train,x_test,y_train,y_test),create_stats(x_train, x_test, y_train, y_test)],axis=0)
+    return stats
+
+
diff --git a/q15_select_best_model/tests/__pycache__/__init__.cpython-36.pyc b/q15_select_best_model/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q15_select_best_model/tests/__pycache__/test.cpython-36.pyc b/q15_select_best_model/tests/__pycache__/test.cpython-36.pyc