diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..ee22e7c
Binary files /dev/null and b/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q01_missing_value/__pycache__/__init__.cpython-36.pyc b/q01_missing_value/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..a531f76
Binary files /dev/null and b/q01_missing_value/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q01_missing_value/__pycache__/build.cpython-36.pyc b/q01_missing_value/__pycache__/build.cpython-36.pyc
new file mode 100644
index 0000000..cde5d94
Binary files /dev/null and b/q01_missing_value/__pycache__/build.cpython-36.pyc differ
diff --git a/q01_missing_value/build.py b/q01_missing_value/build.py
index 7dc4d18..0caeecf 100644
--- a/q01_missing_value/build.py
+++ b/q01_missing_value/build.py
@@ -1,3 +1,4 @@
+# %load q01_missing_value/build.py
 # Default imports
 import pandas as pd
 
@@ -5,6 +6,13 @@
 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_data1=housing_data.loc[:,['MasVnrArea', 'GrLivArea']]
+    total =housing_data1.loc[:,['MasVnrArea','GrLivArea']].notnull()
+    total1 =total.notna()
+    housing_data2=housing_data.loc[:,['LotShape', 'GarageType']]
+    total2=housing_data2.loc[:,['LotShape', 'GarageType']].notnull()
+    total3 =total2.notna()
+    return(total1,total3)
 
 
-# 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
new file mode 100644
index 0000000..c8cc27e
Binary files /dev/null and b/q01_missing_value/tests/__pycache__/__init__.cpython-36.pyc differ
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
new file mode 100644
index 0000000..57c2205
Binary files /dev/null and b/q01_missing_value/tests/__pycache__/test_q01_imputation.cpython-36.pyc differ
diff --git a/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc b/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..522a44e
Binary files /dev/null and b/q02_outlier_removal/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q02_outlier_removal/__pycache__/build.cpython-36.pyc b/q02_outlier_removal/__pycache__/build.cpython-36.pyc
new file mode 100644
index 0000000..ffc3805
Binary files /dev/null and b/q02_outlier_removal/__pycache__/build.cpython-36.pyc differ
diff --git a/q02_outlier_removal/build.py b/q02_outlier_removal/build.py
index 74df5f2..b8a9301 100644
--- a/q02_outlier_removal/build.py
+++ b/q02_outlier_removal/build.py
@@ -1,10 +1,21 @@
+# %load q02_outlier_removal/build.py
 # Default imports
+import matplotlib.pyplot as plt
+import seaborn as sns
 import pandas as pd
-
+import numpy as np
 # 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']]
+#housing_data.describe()
+def outlier_removal(housing_data):
+    housing_data1=housing_data[housing_data.loc[:,['MasVnrArea','GrLivArea','LotShape','GarageType','SalePrice']].notnull()]
+    housing_data1=housing_data1.dropna()
+    housing_data2=housing_data1.sort_values(['MasVnrArea', 'GrLivArea','SalePrice'])
+    upper_quartile = np.percentile(housing_data2['SalePrice'],95)
+    h2=(housing_data2[housing_data2['SalePrice']<upper_quartile])
+    return(h2)
 
+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
new file mode 100644
index 0000000..a300992
Binary files /dev/null and b/q02_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc differ
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
new file mode 100644
index 0000000..fcefab5
Binary files /dev/null and b/q02_outlier_removal/tests/__pycache__/test_q02_outlier_removal.cpython-36.pyc differ
diff --git a/q03_skewness_log/__pycache__/__init__.cpython-36.pyc b/q03_skewness_log/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..cb7ddfd
Binary files /dev/null and b/q03_skewness_log/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q03_skewness_log/__pycache__/build.cpython-36.pyc b/q03_skewness_log/__pycache__/build.cpython-36.pyc
new file mode 100644
index 0000000..9eddb1d
Binary files /dev/null and b/q03_skewness_log/__pycache__/build.cpython-36.pyc differ
diff --git a/q03_skewness_log/build.py b/q03_skewness_log/build.py
index f008d0f..aa1f074 100644
--- a/q03_skewness_log/build.py
+++ b/q03_skewness_log/build.py
@@ -1,8 +1,13 @@
+# %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): 
+    data_trans=data.copy()
+    data_trans['GrLivArea']=np.log(data_trans['GrLivArea'])
+    data_trans['SalePrice']=np.log(data_trans['SalePrice'])
+    return(skew(data_trans['GrLivArea']),skew(data_trans['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
new file mode 100644
index 0000000..8149852
Binary files /dev/null and b/q03_skewness_log/tests/__pycache__/__init__.cpython-36.pyc differ
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
new file mode 100644
index 0000000..fe3545d
Binary files /dev/null and b/q03_skewness_log/tests/__pycache__/test_q03_skewness_log.cpython-36.pyc differ
diff --git a/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc b/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..234c713
Binary files /dev/null and b/q03_skewness_sqrt/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc b/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc
new file mode 100644
index 0000000..2f3c2fb
Binary files /dev/null and b/q03_skewness_sqrt/__pycache__/build.cpython-36.pyc differ
diff --git a/q03_skewness_sqrt/build.py b/q03_skewness_sqrt/build.py
index 4bdb0e4..3e29976 100644
--- 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
@@ -5,6 +6,12 @@
 
 ny_housing = pd.read_csv('data/train.csv')
 
+data = pd.read_csv('data/train.csv')
+def skewness_sqrt(data): 
+    data_trans=data.copy()
+    data_trans['GrLivArea']=np.sqrt(data_trans['GrLivArea'])
+    data_trans['SalePrice']=np.sqrt(data_trans['SalePrice'])
+    return(skew(data_trans['GrLivArea']),skew(data_trans['SalePrice']))
+skewness_sqrt(data)
 
-# 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
new file mode 100644
index 0000000..0cbb9d2
Binary files /dev/null and b/q03_skewness_sqrt/tests/__pycache__/__init__.cpython-36.pyc differ
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
new file mode 100644
index 0000000..812ea8c
Binary files /dev/null and b/q03_skewness_sqrt/tests/__pycache__/test-q03_skewness_sqrt.cpython-36.pyc differ
diff --git a/q04_encoding/__pycache__/__init__.cpython-36.pyc b/q04_encoding/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..a217fe7
Binary files /dev/null and b/q04_encoding/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q04_encoding/__pycache__/build.cpython-36.pyc b/q04_encoding/__pycache__/build.cpython-36.pyc
new file mode 100644
index 0000000..f37b018
Binary files /dev/null and b/q04_encoding/__pycache__/build.cpython-36.pyc differ
diff --git a/q04_encoding/build.py b/q04_encoding/build.py
index a52c57f..6eb1f96 100644
--- 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
@@ -5,6 +6,12 @@
 ny_housing = pd.read_csv('data/train.csv')
 housing_data = ny_housing[['MasVnrArea', 'GrLivArea', 'LotShape', 'GarageType', 'SalePrice']]
 
-
-# Write your code here:
+def encoding(housing_data):
+    total12=housing_data[housing_data.notnull()]
+    le = LabelEncoder()
+    #total12['GarageType_label']=total12['GarageType'].fillna('null')
+    total12=pd.concat([total12,pd.get_dummies(total12['GarageType'],prefix=['GarageType_Label'],dummy_na=False,drop_first=False)],axis=1).drop('GarageType',1)
+    total12['LotShape_label']=le.fit_transform(total12['LotShape'])
+    return(total12)
+encoding(housing_data)
 
diff --git a/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc b/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..1f4ec99
Binary files /dev/null and b/q04_encoding/tests/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q04_encoding/tests/__pycache__/test_q04_encoding.cpython-36.pyc b/q04_encoding/tests/__pycache__/test_q04_encoding.cpython-36.pyc
new file mode 100644
index 0000000..f0b808a
Binary files /dev/null and b/q04_encoding/tests/__pycache__/test_q04_encoding.cpython-36.pyc differ