# -*- coding: utf-8 -*-
"""
Created on Wed Sep 23 11:05:38 2020

@author: Lenovo
"""


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import plotly.graph_objects as go
from bokeh.plotting import figure
from bokeh.models import ColumnDataSource,HoverTool
from bokeh.io import show, output_notebook
import random
from scipy.ndimage import gaussian_gradient_magnitude
from PIL import Image
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator
from nltk.corpus import stopwords 
from nltk.tokenize import word_tokenize 
from wordcloud import WordCloud
import seaborn as sns
from matplotlib_venn import venn2
import scipy as sp
import os
import csv


# import datasets
measure= pd.read_csv('C:/Users/Lenovo/Desktop/Challenge/Data/measure.csv')


# show the data
measure.head()



####################
##  Wordcloud
###################


stopwords = set(STOPWORDS)





####### The wordcloud of grammy
def green_color_func(word, font_size, position, orientation, random_state=None,
                    **kwargs):
    return "hsl(140, 25%%, %d%%)" % random.randint(1, 60)
_words = '' 
  
# iterate through the csv file 
for val in measure.COMMENTS: 
      
    # typecaste each val to string 
    val = str(val)
  
    # split the value 
    tokens = val.split()
      
    _words += " ".join(tokens)+" "
  
wordcloud = WordCloud(width = 800, height = 800,
                background_color ='white',
                stopwords = stopwords,
                min_font_size = 10,random_state=1).generate(_words)

# plot the WordCloud image
plt.figure(figsize = (8, 8))
plt.imshow(wordcloud.recolor(color_func=green_color_func, random_state=3),
           interpolation="bilinear")
plt.axis("off")
plt.tight_layout(pad = 0)
plt.show()