In [110]:

    

import plotly
from plotly.offline import download_plotlyjs, init_notebook_mode, iplot
init_notebook_mode() # run at the start of every notebook


    

In [111]:

    

from plotly.offline import plot
from plotly.graph_objs import *
from plotly.tools import FigureFactory as FF
import plotly.plotly as py
import numpy as np


    

In [107]:

    

def plot_pie(labels,values,title):
    fig = {
        'data': [{'labels': labels,
                  'values': values,
                  'type': 'pie'}],
        'layout': {'title': title}
    }
    return iplot(fig,show_link=False)
def plot_barchart(labels,values,titles,maintitle):
    trace1 = Bar(
        x=labels,
        y=values[0],
        name=titles[0]
    )
    trace2 = Bar(
        x=labels,
        y=values[1],
        name=titles[1]
    )
    data = [trace1, trace2]
    layout = Layout(
        title = maintitle,
        barmode='group'
    )
    fig = Figure(data=data, layout=layout)
    return py.iplot(fig,show_link=False)

def plot_scatter(labels,values,titles,maintitle):
    trace0 = Scatter(
        x=labels,
        y=values[0],
        name=titles[0],
        mode='markers',
        marker=dict(
            size=np.array(values[0])/2000,
        )
    )
    trace1 = Scatter(
        x=labels,
        y=values[1],
        name=titles[1],
        mode='markers',
        marker=dict(
            size=np.array(values[1])/2000,
        )
    )
    data = [trace0,trace1]
    layout = Layout(
        title = maintitle,
        showlegend=True,
        height=600,
        width=700,
    )
    fig = Figure(data=data, layout=layout)
    return py.iplot(fig,filename="Scatter")


    

In [4]:

    

import pandas as pd


    

In [5]:

    

data = pd.read_csv('data.csv',encoding='utf-8')
data = data.drop(['Unnamed: 0'],axis=1)


    

In [6]:

    

idata=data[['Reviewer Username','Gender','Age Group','Product Type','Price(Dollar)']]
import plotly.plotly as py
import numpy as np
from plotly.tools import FigureFactory as FF
index=np.random.choice(idata.shape[0], 10)
table = FF.create_table(idata.ix[index])
py.iplot(table,show_link=False)


    

    
Out[6]:

In [7]:

    

ag=data['Age Group'].value_counts()
plot_pie(ag.keys().tolist(),ag.values.tolist(),'Age Group Percentage In Amazon Reviews')


    

In [8]:

    

g = data['Gender'].value_counts()
plot_pie(g.keys().tolist(),g.values.tolist(),'Gender Percentage in Amazon Reviews')


    

In [9]:

    

g = idata['Product Type'].value_counts()
g['others']= g['$0']
g= g.drop('$0')
plot_pie(g.keys().tolist(),g.values.tolist(),'Product Category Distribution')


    

In [89]:

    

females  = idata.where(idata['Gender']=='female').dropna()
males = idata.where(idata['Gender']=='male').dropna()
labels = ['Books','Electronics','Desktop','Others']
values =[]
values.append(males['Product Type'].value_counts().values)
values.append(females['Product Type'].value_counts().values)
titles = ['Male','Female']
plot_barchart(labels,values,titles,'Gender specific categorywise Purchases')


    

    
Out[89]:

In [ ]: