willywildan

#1
def concat_df(train_data, test_data):
  #Returns a concatenated df of training and test set
  return pd.concat([train_data, test_data], sort=True).reset_index(drop=True)

#2
df_train = pd.read_csv('https://storage.googleapis.com/dqlab-dataset/challenge/feature-engineering/titanic_train.csv')
df_test = pd.read_csv('https://storage.googleapis.com/dqlab-dataset/challenge/feature-engineering/titanic_test.csv')
df_all = concat_df(df_train, df_test)

willywildan

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="darkgrid")
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import OneHotEncoder, LabelEncoder, StandardScaler
from sklearn.metrics import roc_curve, auc
from sklearn.model_selection import StratifiedKFold