diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 2e5da7d..f79f9a5 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..4067037 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..82efcc7 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..aad3003 100644 --- a/q01_outlier_removal/build.py +++ b/q01_outlier_removal/build.py @@ -1,8 +1,25 @@ + # Default imports import pandas as pd loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv') loan_data = loan_data.drop('Loan_ID', 1) +loan_data_numerical = loan_data[['ApplicantIncome', 'CoapplicantIncome', 'LoanAmount']] + +def outlier_removal(data): + df = data + qlt = df.quantile(q=0.95) + + df = df.drop(df[(df['ApplicantIncome']>qlt[0])].index) + df = df.drop(df[(df['CoapplicantIncome']>qlt[1])].index) + df = df.drop(df[(df['LoanAmount']>qlt[2])].index) + + return df + +outlier_removal(loan_data) + + + + -# 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..24c56b5 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..17486b8 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..9ef0c13 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..5e115d0 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..415f973 100644 --- a/q02_data_cleaning_all/build.py +++ b/q02_data_cleaning_all/build.py @@ -1,8 +1,10 @@ +# %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.preprocessing import Imputer from sklearn.model_selection import train_test_split from greyatomlib.logistic_regression_project.q01_outlier_removal.build import outlier_removal @@ -10,5 +12,22 @@ loan_data = loan_data.drop('Loan_ID', 1) loan_data = outlier_removal(loan_data) +def data_cleaning(data): + df = data + imputer_mean = Imputer(missing_values='NaN', strategy='mean') + imputer_mean.fit(df[['LoanAmount']]) + df['LoanAmount'] = imputer_mean.transform(df[['LoanAmount']]) + cat_features = ['Gender', 'Married', 'Dependents', 'Self_Employed', 'Loan_Amount_Term', 'Credit_History'] + for feature in cat_features: + df[feature] = df[feature].fillna(df[feature].mode()[0]) + X = df.iloc[:,:-1] + y = df.iloc[:,-1] + + np.random.seed(9) + X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.25, train_size=0.75) + return X, y, X_train, X_test, y_train, y_test + +data_cleaning(loan_data) + + -# 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..a7da9c4 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..5e08092 Binary files /dev/null and b/q02_data_cleaning_all/tests/__pycache__/test_q02_data_cleaning.cpython-36.pyc differ diff --git a/q02_data_cleaning_all_2/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all_2/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..b522424 Binary files /dev/null and b/q02_data_cleaning_all_2/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_data_cleaning_all_2/__pycache__/build.cpython-36.pyc b/q02_data_cleaning_all_2/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000..2c79946 Binary files /dev/null and b/q02_data_cleaning_all_2/__pycache__/build.cpython-36.pyc differ diff --git a/q02_data_cleaning_all_2/build.py b/q02_data_cleaning_all_2/build.py index e20ff7b..ab63e6c 100644 --- a/q02_data_cleaning_all_2/build.py +++ b/q02_data_cleaning_all_2/build.py @@ -1,3 +1,4 @@ +# %load q02_data_cleaning_all_2/build.py # Default Imports import pandas as pd import numpy as np @@ -9,5 +10,25 @@ loan_data = outlier_removal(loan_data) X, y, X_train, X_test, y_train, y_test = data_cleaning(loan_data) +def data_cleaning_2(X_train, X_test, y_train, y_test): + + numeric_feature = ['ApplicantIncome', 'CoapplicantIncome', 'LoanAmount', 'Loan_Amount_Term','Credit_History'] + cat_features = ['Gender', 'Married', 'Dependents', 'Education', 'Self_Employed', 'Property_Area'] + + for feature in numeric_feature: + X_train[feature] = np.sqrt(X_train[feature]) + X_test[feature] = np.sqrt(X_test[feature]) + + X_train_dummy = pd.get_dummies(X_train[cat_features], drop_first=True) + X_test_dummy = pd.get_dummies(X_test[cat_features], drop_first=True) + X_train = X_train[numeric_feature].join(X_train_dummy) + X_test = X_test[numeric_feature].join(X_test_dummy) + y_train, y_test = y_train, y_test + + return X_train, X_test, y_train, y_test + +data_cleaning_2(X_train, X_test, y_train, y_test) + + + -# Write your solution here : diff --git a/q02_data_cleaning_all_2/tests/__pycache__/__init__.cpython-36.pyc b/q02_data_cleaning_all_2/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..cbd99a2 Binary files /dev/null and b/q02_data_cleaning_all_2/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q02_data_cleaning_all_2/tests/__pycache__/q02_test_data_cleaning_2.cpython-36.pyc b/q02_data_cleaning_all_2/tests/__pycache__/q02_test_data_cleaning_2.cpython-36.pyc new file mode 100644 index 0000000..a3629c8 Binary files /dev/null and b/q02_data_cleaning_all_2/tests/__pycache__/q02_test_data_cleaning_2.cpython-36.pyc differ diff --git a/q03_logistic_regression/__pycache__/__init__.cpython-36.pyc b/q03_logistic_regression/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..e25558b Binary files /dev/null and b/q03_logistic_regression/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_logistic_regression/__pycache__/build.cpython-36.pyc b/q03_logistic_regression/__pycache__/build.cpython-36.pyc new file mode 100644 index 0000000..856fd30 Binary files /dev/null and b/q03_logistic_regression/__pycache__/build.cpython-36.pyc differ diff --git a/q03_logistic_regression/build.py b/q03_logistic_regression/build.py index cdbd506..385380f 100644 --- a/q03_logistic_regression/build.py +++ b/q03_logistic_regression/build.py @@ -1,5 +1,7 @@ +# %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 @@ -13,6 +15,24 @@ 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 + + + + + -# Write your solution code here: diff --git a/q03_logistic_regression/tests/__pycache__/__init__.cpython-36.pyc b/q03_logistic_regression/tests/__pycache__/__init__.cpython-36.pyc new file mode 100644 index 0000000..035698f Binary files /dev/null and b/q03_logistic_regression/tests/__pycache__/__init__.cpython-36.pyc differ diff --git a/q03_logistic_regression/tests/__pycache__/test_q03_logistic_regression.cpython-36.pyc b/q03_logistic_regression/tests/__pycache__/test_q03_logistic_regression.cpython-36.pyc new file mode 100644 index 0000000..9771976 Binary files /dev/null and b/q03_logistic_regression/tests/__pycache__/test_q03_logistic_regression.cpython-36.pyc differ