import pandas as pd
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer
import matplotlib.pyplot as plt
from math import log,sqrt/
import numpy as np
import pandas as pd
#face detection.

data = pd.read_csv("data.csv")

data

import seaborn as sb

import matplotlib
import numpy as np

ef=pd.read_csv("weather.csv")

ef

#What is the size of the dataset?
len(ef)

#How many missing dewpoints are in the dataset?
len(ef[ef["Dewpoint"].isnull()])

#How many missing Rainfall are there?
len(ef[ef["Rainfall"].isnull()])

#Remove the rainfall row containing missing values.
ef[ef["Rainfall"].isnull()].drop()

#Replace the dewpoint row containing the missing value by the mean of the dewpoint column.
j=ef["Dewpoint"].mean()

ef[ef["Dewpoint"].isnull()]=j

ef

ef["Rainfall"].sort_values()

#Sort and print the dataset according to the dewpoint column
ef["Dewpoint"].sort_values()

#What is the mean of rainfall?
ef["Rainfall"].mean()

#What is the standard deviation of dewpoint?
for e in ef:
    p=(ef["Rainfall"]-ef["Rainfall"].mean())**2
    j=p.sum()
i=0
k=0
while(i>=j):
    if(j%i==0):
        k=j%i+k
    i=i+1
print(k)
    

#Plot the dataset rainfall as axis
sb.scatterplot("Rainfall","Dewpoint",data=ef)

#Can you make any conclusion related to the plot?
s='''The rain falls values Greater than 80, the Due points Vary frequently,
The Due point Go on Increasing for the increased value of Rainfall'''

data.head()

t=data["SALES"].shape[0]
ti,tsi=list(),list()
for i in range(data.shape[0]):
    if np.random.uniform(0,1)<0.75:
        ti+=[i]
    else:
        tsi+=[i]
td=data.loc[ti]
ttd=data.loc[tsi]

td.head()

t=data["SALES"].shape[0]

spam_words=' '.join(list(data[data["ORDERNUMBER"]==0]["SALES"]))
spam_wc=WordCloud(width=512,height=512).generate(spam_words)
plt.figure(figsize=(10,8),facecolor='k')
plt.imshow(spam_wc)
plt.axis('off')
plt.tight.layout(pad=0)
plt.show()