commit-live-students · sannidh · Nov 11, 2018 · Nov 11, 2018 · Nov 11, 2018 · Nov 11, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/images/res.png b/images/res.png
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 +1,9 @@
+# %load q01_load_data/build.py
 import pandas as pd
 
-# Write your code below
-
+def load_data(path):
+    df = pd.read_csv(filepath_or_buffer=path, delimiter=';')
+    return df
+
+
+
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 greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 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_data(df1):
+    X = df1.drop(df1.columns[len(df1.columns)-1], axis=1)
+    y = df1.iloc[:,-1]
+    X_train, X_test, y_train, y_test = train_test_split(X,y, train_size=0.7, test_size=0.3)
+    return X_train, X_test, y_train, y_test
+
+
+
+
+
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
@@ -7,8 +8,16 @@
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 
-# Write your code below
-
-
+def label_encode(X_train, X_test):
+    numeric_features = [a for a in range(len(df.dtypes)) if df.dtypes[a] in ['int64','float64']]
+    cat_features = df.columns.difference(df.columns[numeric_features])
+    label_encoder = LabelEncoder()
+    X_transform = X_train.copy()
+    X_test_transform = X_test.copy()
+    for feature in cat_features:
+        X_transform[feature] = label_encoder.fit_transform(X_train[feature])
+        X_test_transform[feature] = label_encoder.fit_transform(X_test[feature])
+    return X_transform, X_test_transform
+
 
 
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
@@ -1,3 +1,4 @@
+# %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
@@ -11,9 +12,12 @@
 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, X_test, category_index=category_index):
+    X_transform = pd.get_dummies(X.iloc[category_index], drop_first=True)
+    X_test_transform = pd.get_dummies(X_test.iloc[category_index], drop_first=True)
+    return  X_transform, X_test_transform
+
+
+
 
-
 
-
-
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 +1,20 @@
-# -*- 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
-
+from greyatomlib.multivariate_regression_project.q04_data_visualisation.build import visualise_data
 import matplotlib.pyplot as plt
+import seaborn as sns
 from pandas.plotting import scatter_matrix
 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)
+df_train = x_train.join(y_train)
+def visualize_data(df_train, path):
+    plot = scatter_matrix(df_train)
+    plt.show();
+    return plot
+
+
 
-# Write your code below
-
-
-
 
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)
 
+def linear_regression(X,y):
+    model = LinearRegression()
+    lm = model.fit(X,y)
+    return lm
+
+
 
-# Write your code below
-
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
@@ -1,10 +1,11 @@
+# %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
 
 from greyatomlib.multivariate_regression_project.q05_linear_regression_model.build import linear_regression
 
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
-
+from greyatomlib.multivariate_regression_project.q06_cross_validation.build import cross_validation_regressor
 from sklearn.model_selection import cross_val_score
 from sklearn.model_selection import KFold
 import numpy as np
@@ -17,5 +18,11 @@
 
 model =linear_regression(x_train,y_train)
 
-# Write your code below
-
+def cross_validation(model, X, y):
+    model.fit(x_train, y_train)
+    scores = cross_val_score(model, X, y)
+    r2_score_mean = np.mean(scores)
+    return r2_score_mean
+
+
+
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
@@ -1,6 +1,7 @@
+# %load q07_regression_pred/build.py
 
 from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score
-
+from sklearn.linear_model import LinearRegression
 from greyatomlib.multivariate_regression_project.q01_load_data.build import load_data
 from greyatomlib.multivariate_regression_project.q02_data_split.build import split_dataset
 
@@ -19,4 +20,14 @@
 val = cross_validation_regressor(model,x_train,y_train)
 
 
-# Write your code below    
+def regression_predictor(model, X, y):
+    model.fit(x_train,y_train)
+    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
+
+
+
+
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
@@ -11,10 +12,17 @@
 df = load_data('data/student-mat.csv')
 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)
+model = linear_regression(x_train,y_train)
 val = cross_validation_regressor(model,x_train,y_train)
 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 = model.fit(x_train, y_train)
+    y_pred = model.predict(x_test)
+    stats1 = pd.DataFrame([[val, mae, mse,  r2]], columns=['cross_validation', 'mae', 'mse', 'r2'])
+    return G, y_pred, stats1
+
+
+
+
+
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
@@ -1,11 +1,15 @@
+# %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
 
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
 
 from greyatomlib.multivariate_regression_project.q07_regression_pred.build import regression_predictor
+from greyatomlib.multivariate_regression_project.q09_advanced_model_q01_lasso.build import lasso
+
 from sklearn.linear_model import Lasso
+from sklearn import linear_model
 import numpy as np
 import pandas as pd
 
@@ -18,6 +22,15 @@
 
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your solution here
 
-
+def lasso_model(x_train, x_test, y_train, alpha=0.1):
+    model = Lasso(alpha)
+    G = model.fit(x_train, y_train)
+    y_pred = model.predict(x_test)
+    val = cross_validation_regressor(model,x_train,y_train)
+    y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
+    stats1 = pd.DataFrame([[val, mae, mse,  r2]], columns=['cross_validation', 'mae', 'mse', 'r2'])
+    return G, y_pred, stats1
+
+
+
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
@@ -1,10 +1,12 @@
+# %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
 
 from greyatomlib.multivariate_regression_project.q03_data_encoding.build import label_encode
 
 from greyatomlib.multivariate_regression_project.q07_regression_pred.build import regression_predictor
+from greyatomlib.multivariate_regression_project.q09_advanced_model_q02_ridge.build import ridge
 from sklearn.linear_model import Ridge
 import numpy as np
 import pandas as pd
@@ -18,8 +20,14 @@
 
 x_train,x_test = label_encode(x_train,x_test)
 
-# Write your code below
-
+def ridge_model(x_train, x_test, y_train, alpha=0.1):
+    model = Ridge(alpha)
+    G = model.fit(x_train, y_train)
+    y_pred = model.predict(x_test)
+    val = cross_validation_regressor(model,x_train,y_train)
+    y_pred, mse, mae, r2 = regression_predictor(model, x_test, y_test)
+    stats1 = pd.DataFrame([[val, mae, mse,  r2]], columns=['cross_validation', 'mae', 'mse', 'r2'])
+    return G, y_pred, stats1
+
 
-
 
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
@@ -1,13 +1,15 @@
+# %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
 import numpy as np
 np.random.seed(9)
 import pandas as pd
 df = load_data('data/student-mat.csv')
-
 x_train, x_test, y_train, y_test =  split_dataset(df)
-x_train,x_test = label_encode(x_train,x_test)
+x_train,x_test = label_encode(x_train,x_test) 
+def describe_df(df):
+    return df.describe(), x_train.apply(pd.value_counts)
+describe_df(df)
+
 
-# Write your code below
-
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
@@ -1,26 +1,30 @@
+# %load q11_feature_selection_q01_plot_corr/build.py
 
 import matplotlib.pyplot as plt
+import pandas as pd
 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')
 
 x_train, x_test, y_train, y_test =  split_dataset(df)
 x_train,x_test = label_encode(x_train,x_test)
 
+def plot_corr(df, size=11):
+    x_train, x_test, y_train, y_test =  split_dataset(df)
+    df_train = pd.concat([x_train,y_train], axis=1)
+    corr = df_train.corr()
+    fig, ax = subplots(figsize=(size,size))
+    plt.set_cmap('YlOrRd')
+    ax.matshow(corr)
+    xticks(range(len(corr.columns)), corr.columns, rotation=90)
+    yticks(range(len(corr.columns)), corr.columns)
+    fig.savefig('./images/data_image.png')
+    return ax
 
-# =============================================================================
-# To visualise data, you need to pass training data only as the assumption holds that test set is unknown data and obviously,you cant not make decision based on unseen data :-p
 
-#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")
 
-# Write your solution here:
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
@@ -19,9 +20,14 @@
 
 
 np.random.seed(9)
-# Write your code below
-
 
+def percentile_k_features(features, labels, k=50):
+    selector = SelectPercentile(f_regression, percentile=k)
+    selector.fit(features, labels)
+    idx_selected = selector.get_support(indices=True)
+    idx_sorted = [idx_selected for _, idx_selected in sorted(zip(selector.scores_[idx_selected], idx_selected), reverse=True)]
+    top_k_predictors = x_train.iloc[:, idx_sorted]
+    return list(top_k_predictors.columns.values)
 
 
 
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
@@ -1,4 +1,4 @@
-# import matplotlib.pyplot as plt
+# %load q12_feature_selection/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
 
@@ -7,12 +7,18 @@
 from greyatomlib.multivariate_regression_project.q11_feature_selection_q02_best_k_features.build import percentile_k_features
 
 from greyatomlib.multivariate_regression_project.q11_feature_selection_q01_plot_corr.build import plot_corr
-
+from greyatomlib.multivariate_regression_project.q12_feature_selection.build import feature_selection
 
 import pandas as pd
 df = load_data('data/student-mat.csv')
-
+X = df.drop(df.columns[len(df.columns)-1], axis=1)
+y = df.iloc[:,-1]
 x_train, x_test, y_train, y_test =  split_dataset(df)
-x_train,x_test = label_encode(x_train,x_test)
+X,_ = label_encode(X,x_train)
+
+def pick_features(X, y, k=50):
+    k_best_features = percentile_k_features(X, y, k)
+    return k_best_features
+
+
 
-# Write your code below
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