import pandas as pd
import numpy as np

from scipy.stats import skew

import seaborn as sns

import plotly.express as ex

from sklearn.model_selection import train_test_split, KFold, StratifiedKFold
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import f1_score

from xgboost import XGBClassifier
from catboost import CatBoostClassifier

import matplotlib.pyplot as plt
%matplotlib inline

import warnings
warnings.filterwarnings('ignore')

from IPython.core.display import display, HTML
display(HTML("<style>.container { width:100% !important; }</style>"))

org_train_data = pd.read_csv('train.csv')
org_test_data = pd.read_csv('test.csv')
sample = pd.read_csv('sample_submission.csv')

train_data = org_train_data.drop(['Accident_ID'],axis=1)
train_data.Severity = train_data.Severity.astype('category')
# train_data.Severity = train_data.Severity.str.replace('Minor_Damage_And_Injuries','0')
# train_data.Severity = train_data.Severity.str.replace('Significant_Damage_And_Fatalities','1')
# train_data.Severity = train_data.Severity.str.replace('Significant_Damage_And_Serious_Injuries','2')
# train_data.Severity = train_data.Severity.str.replace('Highly_Fatal_And_Damaging','3')

# train_data.Severity= train_data.Severity.astype('int64')

train_data.Severity= train_data.Severity.cat.rename_categories({'Minor_Damage_And_Injuries':0, 
                                                                'Significant_Damage_And_Fatalities':1,
                                                               'Significant_Damage_And_Serious_Injuries':2,
                                                               'Highly_Fatal_And_Damaging':3})
train_data.Severity= train_data.Severity.astype('int64')

test_data = org_test_data.drop('Accident_ID',axis=1)

train_data.head()

# print(org_train_data.info())
# print(org_test_data.info())