import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import sklearn
import seaborn as sns

import sklearn 
import plotly.express as px
import plotly.figure_factory as ff
from plotly.subplots import make_subplots
import plotly.graph_objects as go
from plotly.offline import init_notebook_mode, iplot
init_notebook_mode(connected=True)
from sklearn.pipeline import Pipeline

from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from xgboost import XGBClassifier
from lightgbm import LGBMClassifier
from catboost import CatBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import GridSearchCV, RandomizedSearchCV
import time

pd.options.display.max_columns = None
pd.options.display.max_rows = None

import os
for dirname, _, filenames in os.walk('/kaggle/input'):
    for filename in filenames:
        print(os.path.join(dirname, filename))

train=pd.read_csv('train.csv')
test=pd.read_csv('test.csv')
train.head()

train.info()

px.imshow(train.isna(),title="Null Heatmap")

# the categorical features are
cat_feats=['HomePlanet', 'CryoSleep', 'Destination', 'VIP']
px.histogram(
    train,
    x='CryoSleep',
    color='Transported',
    barmode='group',
    width=500,
    height=500
)

px.histogram(
    train,
    x='HomePlanet',
    color='Transported',
    barmode='group',
    width=600,
    height=600,
    title="Home PLanet"
)

px.histogram(
    train,
    x='Destination',
    color='Transported',
    barmode='group',
    width=600,
    height=600
)

px.histogram(
    train,
    x='VIP',
    color='Transported',
    barmode='group',
    width=600,
    height=600
)

px.histogram(
    train,
    x='Age',
    color='Transported',
    marginal='box',
    color_discrete_sequence=['turquoise','blue']
)

fig=make_subplots(
    rows=5,
    cols=1,
)
fig.add_trace(go.Violin(x=train['FoodCourt'],name='Food Court'),row=5,col=1)
fig.add_trace(go.Violin(x=train['FoodCourt'],name='Food Court'),row=1,col=1)
fig.add_trace(go.Violin(x=train['ShoppingMall'],name='Shopping Mall'),row=2,col=1)
fig.add_trace(go.Violin(x=train['Spa'],name='Spa'),row=3,col=1)
fig.add_trace(go.Violin(x=train['VRDeck'],name='VR Deck'),row=4,col=1)

fig.show()