commit-live-students · sunilhariharan · Nov 15, 2018 · Nov 15, 2018 · Nov 15, 2018 · Nov 15, 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 +1,21 @@
+# %load q01_missing_value/build.py
 # Default imports
 import pandas as pd
-
+import numpy as np
+import statistics
 # Data loading
 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']]
 
 
 # Write your code here:
+def imputation(dataset):
+    categoricals = housing_data.select_dtypes(exclude=[np.number])
+    categoricals['GarageType'].fillna(statistics.mode(categoricals['GarageType'].values), inplace = True)
+
+    numericals = housing_data.select_dtypes(include=[np.number])
+    numericals.fillna(numericals.mean(),inplace=True)
+    return numericals,categoricals
+
+
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
@@ -1,3 +1,4 @@
+# %load q02_outlier_removal/build.py
 # Default imports
 import pandas as pd
 
@@ -8,3 +9,11 @@
 
 
 # Write your code here:
+def outlier_removal(dataset):
+    q1=housing_data.quantile(0.95)
+    df =housing_data.drop(housing_data[(housing_data['GrLivArea']>2466.1)].index)
+    df1=df.drop(df[(df['MasVnrArea']>456.0)].index)
+    df2=df1.drop(df1[(df1['SalePrice']>326099.99999999994)].index)
+    return df2
+
+
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
@@ -1,3 +1,4 @@
+# %load q03_skewness_log/build.py
 from scipy.stats import skew
 import pandas as pd
 import numpy as np
@@ -6,3 +7,11 @@
 
 
 # Write code here:
+def skewness_log(data):
+    s1=np.log(data['GrLivArea'])
+    skw1=skew(s1)
+    s2=np.log(data['SalePrice'])
+    skw2=skew(s2)
+    return skw1,skw2
+
+
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
@@ -1,3 +1,4 @@
+# %load q03_skewness_sqrt/build.py
 # Default imports
 from scipy.stats import skew
 import pandas as pd
@@ -7,4 +8,12 @@
 
 
 # Write your Solution Here:
+def skewness_sqrt(data):
+    s1=np.sqrt(data['GrLivArea'])
+    skw1=skew(s1)
+    s2=np.sqrt(data['SalePrice'])
+    skw2=skew(s2)
+    return skw1,skw2
+
+
 
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
@@ -1,3 +1,4 @@
+# %load q04_encoding/build.py
 # Default imports
 import pandas as pd
 from sklearn.preprocessing import LabelEncoder
@@ -7,4 +8,15 @@
 
 
 # Write your code here:
+def encoding(dataset):
+    lablel_encoder = LabelEncoder()
+    housing_data['LotShape_Label'] = lablel_encoder.fit_transform(housing_data['LotShape'])
+
+    dummies=pd.get_dummies(housing_data['GarageType'])
+    new_data=pd.concat([housing_data, dummies], axis = 1)
+    new_data=new_data.drop('GarageType',axis=1)
+    return new_data
+
+
+
 
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