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")
# %load q03_logistic_regression/build.py
# Default Imports
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
from greyatomlib.logistic_regression_project.q01_outlier_removal.build import outlier_removal
from greyatomlib.logistic_regression_project.q02_data_cleaning_all.build import data_cleaning
from greyatomlib.logistic_regression_project.q02_data_cleaning_all_2.build import data_cleaning_2
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)
def logistic_regression(X_train, X_test, y_train, y_test):
column_transform = ['ApplicantIncome', 'CoapplicantIncome', 'LoanAmount']
stand_scale = StandardScaler()
X_train.loc[:, column_transform] = stand_scale.fit_transform(X_train.loc[:, column_transform])
X_test.loc[:, column_transform] = stand_scale.fit_transform(X_test.loc[:, column_transform])
lr = LogisticRegression(random_state=9)
lr.fit(X_train, y_train)
y_pred = lr.predict(X_test)
cm = confusion_matrix(y_test,y_pred)
return cm
