diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc
index 2e5da7d..f242d70 100644
Binary files a/__pycache__/__init__.cpython-36.pyc and b/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q01_outlier_removal/__pycache__/__init__.cpython-36.pyc b/q01_outlier_removal/__pycache__/__init__.cpython-36.pyc
index 2f9a42a..2158d58 100644
Binary files a/q01_outlier_removal/__pycache__/__init__.cpython-36.pyc and b/q01_outlier_removal/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q01_outlier_removal/__pycache__/build.cpython-36.pyc b/q01_outlier_removal/__pycache__/build.cpython-36.pyc
index 8248a16..f2fbee3 100644
Binary files a/q01_outlier_removal/__pycache__/build.cpython-36.pyc and b/q01_outlier_removal/__pycache__/build.cpython-36.pyc differ
diff --git a/q01_outlier_removal/build.py b/q01_outlier_removal/build.py
index ec278ba..5b458c8 100644
--- a/q01_outlier_removal/build.py
+++ b/q01_outlier_removal/build.py
@@ -1,8 +1,27 @@
+# %load q01_outlier_removal/build.py
 # Default imports
 import pandas as pd
+from sklearn.preprocessing import Imputer
 
 loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv')
 loan_data = loan_data.drop('Loan_ID', 1)
 
+def outlier_removal(loan_data):
+    qv=loan_data[['ApplicantIncome','CoapplicantIncome','LoanAmount']].quantile(0.95)
+#     return loan_data[((loan_data[['ApplicantIncome','CoapplicantIncome','LoanAmount']]<=qv).all(axis=1))]
+#     return loan_data[(loan_data['ApplicantIncome']<qv[0])& (loan_data['CoapplicantIncome']<qv[1])&(loan_data['LoanAmount']<qv[2])]
+    imp_mean = Imputer(missing_values='NaN',strategy='mean')
+    imp_mean.fit(loan_data[['ApplicantIncome','CoapplicantIncome','LoanAmount']])
+    loan_data[['ApplicantIncome','CoapplicantIncome','LoanAmount']] = imp_mean.transform(loan_data[['ApplicantIncome','CoapplicantIncome','LoanAmount']])
+    
+    
+    return loan_data[(loan_data['ApplicantIncome']<=loan_data['ApplicantIncome'].quantile(0.95))& (loan_data['CoapplicantIncome']<=loan_data['CoapplicantIncome'].quantile(0.95))& (loan_data['LoanAmount']<=loan_data['LoanAmount'].quantile(0.95))]
+    
+    
+    
+    
+c=outlier_removal(loan_data)
+c.shape
+
+
 
-# Write your Solution here:
diff --git a/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc b/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc
index 5a057ff..988f8b6 100644
Binary files a/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc and b/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q01_outlier_removal/tests/__pycache__/test_q01_outlier_removal.cpython-36.pyc b/q01_outlier_removal/tests/__pycache__/test_q01_outlier_removal.cpython-36.pyc
index 4c0b6c7..5e7dee5 100644
Binary files a/q01_outlier_removal/tests/__pycache__/test_q01_outlier_removal.cpython-36.pyc and b/q01_outlier_removal/tests/__pycache__/test_q01_outlier_removal.cpython-36.pyc differ
diff --git a/q02_data_cleaning_all/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..0192845
Binary files /dev/null and b/q02_data_cleaning_all/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q02_data_cleaning_all/__pycache__/build.cpython-36.pyc b/q02_data_cleaning_all/__pycache__/build.cpython-36.pyc
new file mode 100644
index 0000000..3f5321d
Binary files /dev/null and b/q02_data_cleaning_all/__pycache__/build.cpython-36.pyc differ
diff --git a/q02_data_cleaning_all/build.py b/q02_data_cleaning_all/build.py
index b56e2bc..53db425 100644
--- a/q02_data_cleaning_all/build.py
+++ b/q02_data_cleaning_all/build.py
@@ -1,14 +1,35 @@
+# %load q02_data_cleaning_all/build.py
 # Default Imports
 import sys, os
 sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname('__file__'))))
 import pandas as pd
 import numpy as np
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split as tts
 from greyatomlib.logistic_regression_project.q01_outlier_removal.build import outlier_removal
 
 loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv')
 loan_data = loan_data.drop('Loan_ID', 1)
 loan_data = outlier_removal(loan_data)
 
+from sklearn.preprocessing import Imputer
+
+# imp_mean = Imputer(missing_values='NaN',strategy='mean')
+# imp_mean.fit(loan_data['LoanAmount'])
+# loan_data['LoanAmount'] = imp_mean.transform(loan_data['LoanAmount'])
+def data_cleaning(loan_data):
+    loan_data['LoanAmount'] = (loan_data['LoanAmount']).fillna(loan_data['LoanAmount'].mean())
+
+    loan_data['Gender']=loan_data['Gender'].fillna(loan_data['Gender'].mode)
+    # loan_data[['Gender', 'Married', 'Dependents', 'Self_Employed', 'Loan_Amount_Term', 'Credit_History']]
+    loan_data['Married']=loan_data['Married'].fillna(loan_data['Married'].mode)
+    loan_data['Dependents']=loan_data['Dependents'].fillna(loan_data['Dependents'].mode)
+    loan_data['Self_Employed']=loan_data['Self_Employed'].fillna(loan_data['Self_Employed'].mode)
+    loan_data['Loan_Amount_Term']=loan_data['Loan_Amount_Term'].fillna(loan_data['Loan_Amount_Term'].mode)
+    loan_data['Credit_History']=loan_data['Credit_History'].fillna(loan_data['Credit_History'].mode)
+    X = loan_data.drop(['Loan_Status'],axis=1)
+    y = loan_data['Loan_Status']
+    X_train,X_test,y_train,y_test = tts(X,y,test_size=0.25,random_state=9)
+    return X,y,X_train,X_test,y_train,y_test 
+
+
 
-# Write your solution here :
diff --git a/q02_data_cleaning_all/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all/tests/__pycache__/__init__.cpython-36.pyc
new file mode 100644
index 0000000..d0fb196
Binary files /dev/null and b/q02_data_cleaning_all/tests/__pycache__/__init__.cpython-36.pyc differ
diff --git a/q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc b/q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc
new file mode 100644
index 0000000..fd582a8
Binary files /dev/null and b/q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc differ