commit-live-students · Abhimanyu22 · Nov 3, 2018 · Nov 3, 2018 · Nov 3, 2018 · Nov 3, 2018
diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_missing_value/__pycache__/__init__.cpython-36.pyc b/q01_missing_value/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_missing_value/__pycache__/build.cpython-36.pyc b/q01_missing_value/__pycache__/build.cpython-36.pyc
diff --git a/q01_missing_value/build.py b/q01_missing_value/build.py
@@ -1,10 +1,25 @@
-# Default imports
 import pandas as pd
+from sklearn.preprocessing import Imputer
+import warnings
 
-# Data loading
-ny_housing = pd.read_csv('data/train.csv')
+ny_housing = pd.read_csv('./data/train.csv')
 # Selecting 4 most relevant variables along with target variable from the dataset fot the Cleaning and Preprocessing.
 housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']]
 
+def imputation(housing_data):
+
+    housing_data['MasVnrArea'] = housing_data['MasVnrArea'].fillna(housing_data['MasVnrArea'].mean())
+    housing_data['GrLivArea'] = housing_data['GrLivArea'].fillna(housing_data['GrLivArea'].mean())
+    housing_data['SalePrice'] = housing_data['SalePrice'].fillna(housing_data['SalePrice'].mean())
+
+    housing_data['LotShape'] = housing_data['LotShape'].fillna(housing_data['LotShape'].mode()[0])
+    housing_data['GarageType'] = housing_data['GarageType'].fillna(housing_data['GarageType'].mode()[0])
+
+    return housing_data[['MasVnrArea', 'GrLivArea', 'SalePrice']], housing_data[['LotShape', 'GarageType']]
+
+imputation(housing_data)
+
+
+
+
 
-# Write your code here:
diff --git a/q01_missing_value/tests/__pycache__/__init__.cpython-36.pyc b/q01_missing_value/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q01_missing_value/tests/__pycache__/test_q01_imputation.cpython-36.pyc b/q01_missing_value/tests/__pycache__/test_q01_imputation.cpython-36.pyc
diff --git a/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_outlier_removal/__pycache__/build.cpython-36.pyc b/q02_outlier_removal/__pycache__/build.cpython-36.pyc
diff --git a/q02_outlier_removal/build.py b/q02_outlier_removal/build.py
@@ -1,10 +1,21 @@
-# Default imports
 import pandas as pd
 
 # Data
 ny_housing = pd.read_csv('data/train.csv')
 # Selecting 4 most relevant variables from the dataset fot the Cleaning and Preprocessing.
 housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']]
 
+def outlier_removal(housing_data):
+    df = housing_data
+    qlt = housing_data.quantile(q=0.95)
+
+    df = df.drop(df[(df['MasVnrArea']>qlt[0])].index)
+    df = df.drop(df[(df['GrLivArea']>qlt[1])].index)
+    df = df.drop(df[(df['SalePrice']>qlt[2])].index)
+
+    return df
+
+outlier_removal(housing_data)
+
+
 
-# Write your code here:
diff --git a/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc b/q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc
diff --git a/q03_skewness_log/__pycache__/__init__.cpython-36.pyc b/q03_skewness_log/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_skewness_log/__pycache__/build.cpython-36.pyc b/q03_skewness_log/__pycache__/build.cpython-36.pyc
diff --git a/q03_skewness_log/build.py b/q03_skewness_log/build.py
@@ -1,8 +1,22 @@
+# %load q03_skewness_log/build.py
 from scipy.stats import skew
 import pandas as pd
 import numpy as np
 
 data = pd.read_csv('data/train.csv')
 
+def skewness_log(data):
+
+    df = data.copy()
+    df['GrLivArea'] = np.log(df['GrLivArea'])
+    df['SalePrice'] = np.log(df['SalePrice'])
+
+    skewed_grLiv = skew(df['GrLivArea'])
+    skewed_SalePrice = skew(df['SalePrice'])
+
+    return skewed_grLiv, skewed_SalePrice
+
+skewness_log(data)
+
+
 
-# Write code here:
diff --git a/q03_skewness_log/tests/__pycache__/__init__.cpython-36.pyc b/q03_skewness_log/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_skewness_log/tests/__pycache__/test_q03_skewness_log.cpython-36.pyc b/q03_skewness_log/tests/__pycache__/test_q03_skewness_log.cpython-36.pyc
diff --git a/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc b/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc b/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc
diff --git a/q03_skewness_sqrt/build.py b/q03_skewness_sqrt/build.py
@@ -1,10 +1,22 @@
+# %load q03_skewness_sqrt/build.py
 # Default imports
 from scipy.stats import skew
 import pandas as pd
 import numpy as np
 
 ny_housing = pd.read_csv('data/train.csv')
 
+def skewness_sqrt(ny_housing):
+    df = ny_housing.copy()
+    df['GrLivArea'] = np.sqrt(df['GrLivArea'])
+    df['SalePrice'] = np.sqrt(df['SalePrice'])
+
+    skewed_grLiv = skew(df['GrLivArea'])
+    skewed_SalePrice = skew(df['SalePrice'])
+
+    return skewed_grLiv, skewed_SalePrice
+
+skewness_sqrt(ny_housing)
+
 
-# Write your Solution Here:
 
diff --git a/q03_skewness_sqrt/tests/__pycache__/__init__.cpython-36.pyc b/q03_skewness_sqrt/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q03_skewness_sqrt/tests/__pycache__/test-q03_skewness_sqrt.cpython-36.pyc b/q03_skewness_sqrt/tests/__pycache__/test-q03_skewness_sqrt.cpython-36.pyc
diff --git a/q04_encoding/__pycache__/__init__.cpython-36.pyc b/q04_encoding/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_encoding/__pycache__/build.cpython-36.pyc b/q04_encoding/__pycache__/build.cpython-36.pyc
diff --git a/q04_encoding/build.py b/q04_encoding/build.py
@@ -1,10 +1,20 @@
+# %load q04_encoding/build.py
 # Default imports
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder
 
 ny_housing = pd.read_csv('data/train.csv')
 housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']]
 
+def encoding(housing_data):
+    df = housing_data
+    label_encoder = LabelEncoder()
+    df['LotShape_Label'] = label_encoder.fit_transform(df['LotShape'])
+    df = df.join(pd.get_dummies(df['GarageType'], drop_first=True))
+
+    return df
+
+encoding(housing_data)
+
 
-# Write your code here:
 
diff --git a/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc b/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc
diff --git a/q04_encoding/tests/__pycache__/test_q04_encoding.cpython-36.pyc b/q04_encoding/tests/__pycache__/test_q04_encoding.cpython-36.pyc