diff --git a/__pycache__/__init__.cpython-36.pyc b/__pycache__/__init__.cpython-36.pyc index 2e5da7d..7015f0e 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..c7ee446 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..044dcb3 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..533d09b 100644 --- a/q01_outlier_removal/build.py +++ b/q01_outlier_removal/build.py @@ -1,8 +1,25 @@ +# %load q01_outlier_removal/build.py # Default imports import pandas as pd +import numpy as np loan_data = pd.read_csv('data/loan_prediction_uncleaned.csv') loan_data = loan_data.drop('Loan_ID', 1) # Write your Solution here: +def outlier_removal(data): + num_cols = data[['ApplicantIncome','CoapplicantIncome','LoanAmount']] + + quantile_values = num_cols.quantile(0.95) + + for col in num_cols: + quantile = quantile_values[col] + print(quantile) + data = data.drop(data[data[col]>quantile].index) + + return data + +outlier_removal(loan_data) + + diff --git a/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc b/q01_outlier_removal/tests/__pycache__/__init__.cpython-36.pyc index 5a057ff..0eed343 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..436f2f7 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