%reload_ext autoreload
%autoreload 2
%matplotlib inline

# ! pip install kaggle --upgrade
# ! pip install plotly --upgrade

import numpy as np 
import pandas as pd 
from pandas import plotting

import matplotlib.pyplot as plt 
import seaborn as sns 
plt.style.use('fivethirtyeight')

import plotly as py
import plotly.graph_objs as go
py.offline.init_notebook_mode(connected = True)

from sklearn.cluster import KMeans
import fastai

import warnings
import os
from pathlib import Path
warnings.filterwarnings("ignore")

dataset = 'vjchoudhary7/customer-segmentation-tutorial-in-python'

# Google Colab
config_path = Path('/content/drive')
data_path_base = Path('/content/datasets/')

data_path = data_path_base/dataset

from google.colab import drive
drive.mount(str(config_path))
os.environ['KAGGLE_CONFIG_DIR'] = f"{config_path}/My Drive/.kaggle"

# # VM
# config_path = Path(os.getenv("HOME"))
# data_path = config_path/"datasets"/dataset

# data_path.mkdir(parents=True, exist_ok=True)
# os.environ['KAGGLE_CONFIG_DIR'] = f"{config_path}/.kaggle"

!kaggle datasets download {dataset} -p "{data_path}" --unzip

!ls {data_path}

df =  pd.read_csv(data_path/'Mall_Customers.csv')
df.shape

df.head()

df.describe()

df.dtypes

df.isnull().sum()

plt.figure(1 , figsize = (15 , 6))
n = 0 
for x in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
    n += 1
    plt.subplot(1 , 3 , n)
    plt.subplots_adjust(hspace =0.5 , wspace = 0.5)
    sns.distplot(df[x] , bins = 20)
    plt.title('Distplot of {}'.format(x))
plt.show()

labels = ['Female', 'Male']
size = df['Gender'].value_counts()
size

explode = [0, 0.1]

plt.rcParams['figure.figsize'] = (9, 9)
plt.pie(size, explode = explode, labels = labels, shadow = True, autopct = '%.2f%%')
plt.title('Gender', fontsize = 20)
plt.axis('off')
plt.legend()
plt.show()

plt.rcParams['figure.figsize'] = (10, 7)

plotting.andrews_curves(df.drop("CustomerID", axis=1), "Gender")
plt.title('Andrew Curves for Gender', fontsize = 20)
plt.show()

plt.figure(1 , figsize = (10 , 7))
n = 0 
for x in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
    for y in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
        n += 1
        plt.subplot(3 , 3 , n)
        plt.subplots_adjust(hspace = 0.5 , wspace = 0.5)
        sns.regplot(x = x , y = y , data = df)
        plt.ylabel(y.split()[0]+' '+y.split()[1] if len(y.split()) > 1 else y )
plt.show()

g = sns.pairplot(df.drop("CustomerID", axis=1), hue="Gender", height=3)
g.fig.suptitle("Pairplot for the Data", y=1.08) # y= some height>1

plt.figure(1 , figsize = (10 , 6))
for gender in ['Male' , 'Female']:
    plt.scatter(x = 'Age' , y = 'Annual Income (k$)' , data = df[df['Gender'] == gender] ,
                s = 200 , alpha = 0.5 , label = gender)
plt.xlabel('Age'), plt.ylabel('Annual Income (k$)') 
plt.title('Age vs Annual Income w.r.t Gender')
plt.legend()
plt.show()

plt.figure(1 , figsize = (10 , 6))
for gender in ['Male' , 'Female']:
    plt.scatter(x = 'Annual Income (k$)',y = 'Spending Score (1-100)' ,
                data = df[df['Gender'] == gender] ,s = 200 , alpha = 0.5 , label = gender)
plt.xlabel('Annual Income (k$)'), plt.ylabel('Spending Score (1-100)') 
plt.title('Annual Income vs Spending Score w.r.t Gender')
plt.legend()
plt.show()

plt.figure(1 , figsize = (12 , 7))
n = 0 
for cols in ['Age' , 'Annual Income (k$)' , 'Spending Score (1-100)']:
    n += 1 
    plt.subplot(1 , 3 , n)
    plt.subplots_adjust(hspace = 0.5 , wspace = 0.5)
    sns.violinplot(x = cols , y = 'Gender' , data = df , palette = 'vlag')
    sns.swarmplot(x = cols , y = 'Gender' , data = df)
    plt.ylabel('Gender' if n == 1 else '')
    plt.title('Boxplots & Swarmplots' if n == 2 else '')
plt.show()