def test_logistic_regression(self):
# Input parameters tests
args = getargspec(logistic_regression)
self.assertEqual(len(args[0]), 4,
"Expected arguments %d, Given %d" % (4, len(args[0])))
self.assertEqual(
args[3], None,
"Expected default values do not match given default values")
# Return data types
loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv')
loan_data = loan_data.drop('Loan_ID', 1)
loan_data = outlier_removal(loan_data)
X, y, X_train, X_test, y_train, y_test = data_cleaning(loan_data)
X_train, X_test, y_train, y_test = data_cleaning_2(
X_train, X_test, y_train, y_test)
cm = logistic_regression(X_train, X_test, y_train, y_test)
self.assertIsInstance(
cm, numpy.ndarray,
"Expected data type for return value is `numpy.ndarray`, you are returning %s"
% (type(cm)))
# Return value tests
self.assertEqual(cm.max(), 89,
"Expected return value does not given return value")
def test_data_cleaning_2(self):
# Input parameters tests
args = getargspec(data_cleaning_2)
self.assertEqual(len(args[0]), 4,
"Expected arguments %d, Given %d" % (4, len(args[0])))
self.assertEqual(
args[3], None,
"Expected default values do not match given default values")
# Return data types
loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv')
loan_data = loan_data.drop('Loan_ID', 1)
loan_data = outlier_removal(loan_data)
X, y, X_train, X_test, y_train, y_test = data_cleaning(loan_data)
X_train, X_test, y_train, y_test = data_cleaning_2(
X_train, X_test, y_train, y_test)
self.assertIsInstance(
X_test, pd.core.frame.DataFrame,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(X_test)))
self.assertIsInstance(
X_train, pd.core.frame.DataFrame,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(X_train)))
self.assertIsInstance(
y_train, pd.core.series.Series,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(y_train)))
self.assertIsInstance(
y_test, pd.core.series.Series,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(y_test)))
# Return value tests
train_val = X_train['Dependents_1'].value_counts()
train_val1 = X_train['Property_Area_Urban'].value_counts()
test_val = X_test['Property_Area_Urban'].value_counts()
test_val1 = X_test['Dependents_1'].value_counts()
self.assertEqual(
list(train_val), [343, 65],
"Return value counts does not match expected value counts")
self.assertEqual(
list(train_val1), [277, 131],
"Return value counts does not match expected value counts")
self.assertEqual(
list(test_val), [87, 50],
"Return value counts does not match expected value counts")
self.assertEqual(
list(test_val1), [114, 23],
"Return value counts does not match expected value counts")
self.assertEqual(X_train.shape, (408, 14),
"Return value shape does not match expected value")
self.assertEqual(X_test.shape, (137, 14),
"Return value shape does not match expected value")
def test_data_cleaning(self):
# Input parameters tests
args = getargspec(data_cleaning)
self.assertEqual(len(args[0]), 1,
"Expected arguments %d, Given %d" % (1, len(args[0])))
self.assertEqual(
args[3], None,
"Expected default values do not match given default values")
loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv')
loan_data = loan_data.drop('Loan_ID', 1)
loan_data = outlier_removal(loan_data)
X, y, X_train, X_test, y_train, y_test = data_cleaning(loan_data)
# Return data types
self.assertIsInstance(
X_test, pd.core.frame.DataFrame,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(X_test)))
self.assertIsInstance(
X_train, pd.core.frame.DataFrame,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(X_train)))
self.assertIsInstance(
X, pd.core.frame.DataFrame,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(X)))
self.assertIsInstance(
y, pd.core.series.Series,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(y)))
self.assertIsInstance(
y_train, pd.core.series.Series,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(y_train)))
self.assertIsInstance(
y_test, pd.core.series.Series,
"Expected data type for return value is `pandas DataFrame`, you are returning %s"
% (type(y_test)))
# Return value tests
Return_val = X_train.isnull().values.any()
Return_val1 = X_test.isnull().values.any()
self.assertEqual(Return_val, False, "Return value contains NaN values")
self.assertEqual(Return_val1, False,
"Return value contains NaN values")
# Default Imports
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from greyatomlib.logistic_regression_project.q01_outlier_removal.build import outlier_removal
from sklearn.preprocessing import Imputer
loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv')
loan_data = loan_data.drop('Loan_ID', 1)
loan_data = outlier_removal(loan_data)
# Write your solution here :
def data_cleaning(data):
np.random_state=9
imp_mean=Imputer(missing_values='NaN', strategy='mean')
imp_mode=Imputer(missing_values='NaN', strategy='most_frequent')
data['LoanAmount']=imp_mean.fit_transform(data[['LoanAmount']])
data['Gender']=data['Gender'].fillna(data['Gender'].mode()[0])
data['Married']=data['Married'].fillna(data['Married'].mode()[0])
data['Dependents']=data['Dependents'].fillna(data['Dependents'].mode()[0])
data['Married']=data['Married'].fillna(data['Married'].mode()[0])
data['Self_Employed']=data['Self_Employed'].fillna(data['Self_Employed'].mode()[0])
data['Loan_Amount_Term']=data['Loan_Amount_Term'].fillna(data['Loan_Amount_Term'].mode()[0])
data['Credit_History']=data['Credit_History'].fillna(data['Credit_History'].mode()[0])
X=data.iloc[:,:-1]
y=data.iloc[:,-1]
X_train, X_test, y_train, y_test=train_test_split(X,y,test_size=0.25,random_state=9)
return X,y,X_train,X_test,y_train,y_test
