commit-live-students · ramakrishnasonakam · Dec 14, 2018 · Dec 15, 2018 · Dec 15, 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
@@ -1,10 +1,14 @@
+# %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'
-
-
+from sklearn.model_selection import train_test_split    
+path = pd.read_csv('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.iloc[:, -1]
+    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
+
 
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_q01_load_data.cpython-36.pyc b/q01_load_data/tests/__pycache__/test_q01_load_data.cpython-36.pyc
diff --git a/q02_Max_important_feature/__pycache__/__init__.cpython-36.pyc b/q02_Max_important_feature/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_Max_important_feature/__pycache__/build.cpython-36.pyc b/q02_Max_important_feature/__pycache__/build.cpython-36.pyc
diff --git a/q02_Max_important_feature/build.py b/q02_Max_important_feature/build.py
@@ -1,8 +1,14 @@
+# %load q02_Max_important_feature/build.py
 # Default imports
 from greyatomlib.advanced_linear_regression.q01_load_data.build import load_data
 
 # 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')
+target_variable = data_set['SalePrice']
+n = 4
+# Write your code here
+def Max_important_feature(data_set, target_variable = 'SalePrice', n = 4):
+    cor = data_set.corr()[target_variable]
+    return cor.sort_values(ascending=False)[1:n + 1].index.values
 
 
-# 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
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
diff --git a/q03_polynomial/__pycache__/__init__.cpython-36.pyc b/q03_polynomial/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_polynomial/__pycache__/build.cpython-36.pyc b/q03_polynomial/__pycache__/build.cpython-36.pyc
diff --git 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
@@ -7,5 +8,13 @@
 # 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')
 
-
 # Write your solution here
+def polynomial(power = 5, random_state = 9):
+
+    Poly_Xtrain = X_train[['OverallQual', 'GrLivArea', 'GarageCars', 'GarageArea']]
+    Poly_ytrain = y_train
+    poly_features = make_pipeline(PolynomialFeatures(power, include_bias=False), LinearRegression())
+    model = poly_features.fit(Poly_Xtrain, Poly_ytrain)
+    return model
+
+
diff --git a/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc b/q03_polynomial/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_polynomial/tests/__pycache__/test_q03_polynomial.cpython-36.pyc b/q03_polynomial/tests/__pycache__/test_q03_polynomial.cpython-36.pyc