import pandas as pd
df=pd.read_csv(r'D:\BB_internship_Tasks\cloths-rating.csv')
df

	ProductID	UserID	Rating	Text
0	777	AV1YnR7wglJLPUi8IJmi	4	Great taffy at a great price.
1	767	AVpfpK8KLJeJML43BCuD	4	Absolutely wonderful - silky and sexy and comf...
2	1080	AVqkIdntQMlgsOJE6fuB	5	Love this dress! it's sooo pretty.
3	1077	AVpfpK8KLJeJML43BCuD	3	I had such high hopes for this dress and reall...
4	1049	AVpfpK8KLJeJML43BCuD	5	I love, love, love this jumpsuit. it's fun, fl...
...	...	...	...	...
629	823	B08GWV3SM6	1	I placed order 4+1 soaps.But I have received w...
630	823	B08GWV3SM6	3	The soap is ok for bathing, no scent at all, m...
631	847	B08GWV3SM6	5	For a long time I was searching for Indian soa...
632	910	AVph0EeEilAPnD_x9myq	3	Good but not great
633	333	AVqkIdntQMlgsOJE6fuB	5	Quick,easy to make & tasty too.

634 rows × 4 columns

import numpy as np
!pip install textblob
from textblob import TextBlob

Requirement already satisfied: textblob in c:\anaconda\lib\site-packages (0.17.1)
Requirement already satisfied: nltk>=3.1 in c:\anaconda\lib\site-packages (from textblob) (3.7)
Requirement already satisfied: tqdm in c:\anaconda\lib\site-packages (from nltk>=3.1->textblob) (4.64.0)
Requirement already satisfied: regex>=2021.8.3 in c:\anaconda\lib\site-packages (from nltk>=3.1->textblob) (2022.3.15)
Requirement already satisfied: click in c:\anaconda\lib\site-packages (from nltk>=3.1->textblob) (8.0.4)
Requirement already satisfied: joblib in c:\anaconda\lib\site-packages (from nltk>=3.1->textblob) (1.1.0)
Requirement already satisfied: colorama in c:\anaconda\lib\site-packages (from click->nltk>=3.1->textblob) (0.4.4)

def sentiment(text):
    try:
        return TextBlob(str(text)).sentiment.polarity
    except:
        return None
df['sentiment'] = df['Text'].apply(sentiment)
df

	ProductID	UserID	Rating	Text	sentiment
0	777	AV1YnR7wglJLPUi8IJmi	4	Great taffy at a great price.	0.800000
1	767	AVpfpK8KLJeJML43BCuD	4	Absolutely wonderful - silky and sexy and comf...	0.633333
2	1080	AVqkIdntQMlgsOJE6fuB	5	Love this dress! it's sooo pretty.	0.437500
3	1077	AVpfpK8KLJeJML43BCuD	3	I had such high hopes for this dress and reall...	0.120000
4	1049	AVpfpK8KLJeJML43BCuD	5	I love, love, love this jumpsuit. it's fun, fl...	0.550000
...	...	...	...	...	...
629	823	B08GWV3SM6	1	I placed order 4+1 soaps.But I have received w...	0.000000
630	823	B08GWV3SM6	3	The soap is ok for bathing, no scent at all, m...	0.325000
631	847	B08GWV3SM6	5	For a long time I was searching for Indian soa...	-0.025000
632	910	AVph0EeEilAPnD_x9myq	3	Good but not great	0.150000
633	333	AVqkIdntQMlgsOJE6fuB	5	Quick,easy to make & tasty too.	0.000000

634 rows × 5 columns

df['Updated_score'] = df['Rating']*df['sentiment']
df

	ProductID	UserID	Rating	Text	sentiment	Updated_score
0	777	AV1YnR7wglJLPUi8IJmi	4	Great taffy at a great price.	0.800000	3.200000
1	767	AVpfpK8KLJeJML43BCuD	4	Absolutely wonderful - silky and sexy and comf...	0.633333	2.533333
2	1080	AVqkIdntQMlgsOJE6fuB	5	Love this dress! it's sooo pretty.	0.437500	2.187500
3	1077	AVpfpK8KLJeJML43BCuD	3	I had such high hopes for this dress and reall...	0.120000	0.360000
4	1049	AVpfpK8KLJeJML43BCuD	5	I love, love, love this jumpsuit. it's fun, fl...	0.550000	2.750000
...	...	...	...	...	...	...
629	823	B08GWV3SM6	1	I placed order 4+1 soaps.But I have received w...	0.000000	0.000000
630	823	B08GWV3SM6	3	The soap is ok for bathing, no scent at all, m...	0.325000	0.975000
631	847	B08GWV3SM6	5	For a long time I was searching for Indian soa...	-0.025000	-0.125000
632	910	AVph0EeEilAPnD_x9myq	3	Good but not great	0.150000	0.450000
633	333	AVqkIdntQMlgsOJE6fuB	5	Quick,easy to make & tasty too.	0.000000	0.000000

634 rows × 6 columns

b=[-1,-0.75,-0.5,-0.25,0,0.25,0.5,0.75,1]
l=[]
for i in b:
    for j in range(1,6):
        x=i*j
        l.append(x)
print(l)
len(l)

[-1, -2, -3, -4, -5, -0.75, -1.5, -2.25, -3.0, -3.75, -0.5, -1.0, -1.5, -2.0, -2.5, -0.25, -0.5, -0.75, -1.0, -1.25, 0, 0, 0, 0, 0, 0.25, 0.5, 0.75, 1.0, 1.25, 0.5, 1.0, 1.5, 2.0, 2.5, 0.75, 1.5, 2.25, 3.0, 3.75, 1, 2, 3, 4, 5]

45

len(set(l))

27

def equalizer(v):
    if v <= 0:
        return 1
    elif v <= 2:
        return 2
    elif v <= 3:
        return 3
    elif v <= 4:
        return 4
    elif v <= 5:
        return 5

df['New_score'] = df['Updated_score'].apply(equalizer)
df

	ProductID	UserID	Rating	Text	sentiment	Updated_score	New_score
0	777	AV1YnR7wglJLPUi8IJmi	4	Great taffy at a great price.	0.800000	3.200000	4
1	767	AVpfpK8KLJeJML43BCuD	4	Absolutely wonderful - silky and sexy and comf...	0.633333	2.533333	3
2	1080	AVqkIdntQMlgsOJE6fuB	5	Love this dress! it's sooo pretty.	0.437500	2.187500	3
3	1077	AVpfpK8KLJeJML43BCuD	3	I had such high hopes for this dress and reall...	0.120000	0.360000	2
4	1049	AVpfpK8KLJeJML43BCuD	5	I love, love, love this jumpsuit. it's fun, fl...	0.550000	2.750000	3
...	...	...	...	...	...	...	...
629	823	B08GWV3SM6	1	I placed order 4+1 soaps.But I have received w...	0.000000	0.000000	1
630	823	B08GWV3SM6	3	The soap is ok for bathing, no scent at all, m...	0.325000	0.975000	2
631	847	B08GWV3SM6	5	For a long time I was searching for Indian soa...	-0.025000	-0.125000	1
632	910	AVph0EeEilAPnD_x9myq	3	Good but not great	0.150000	0.450000	2
633	333	AVqkIdntQMlgsOJE6fuB	5	Quick,easy to make & tasty too.	0.000000	0.000000	1

634 rows × 7 columns

Label Encoding User id and product id

from sklearn.preprocessing import LabelEncoder

le = LabelEncoder()
df['UserID'] = le.fit_transform(df['UserID'])
df

	ProductID	UserID	Rating	Text	sentiment	Updated_score	New_score
0	777	0	4	Great taffy at a great price.	0.800000	3.200000	4
1	767	3	4	Absolutely wonderful - silky and sexy and comf...	0.633333	2.533333	3
2	1080	13	5	Love this dress! it's sooo pretty.	0.437500	2.187500	3
3	1077	3	3	I had such high hopes for this dress and reall...	0.120000	0.360000	2
4	1049	3	5	I love, love, love this jumpsuit. it's fun, fl...	0.550000	2.750000	3
...	...	...	...	...	...	...	...
629	823	41	1	I placed order 4+1 soaps.But I have received w...	0.000000	0.000000	1
630	823	41	3	The soap is ok for bathing, no scent at all, m...	0.325000	0.975000	2
631	847	41	5	For a long time I was searching for Indian soa...	-0.025000	-0.125000	1
632	910	7	3	Good but not great	0.150000	0.450000	2
633	333	13	5	Quick,easy to make & tasty too.	0.000000	0.000000	1

634 rows × 7 columns

#from sklearn.preprocessing import LabelEncoder

#le = LabelEncoder()
#df['ProductID'] = le.fit_transform(df['ProductID'])
#df

#we assign product name to product id were name is given in json file named pname.json

#le = LabelEncoder()
#df['ProductNAME'] = le.fit_transform(df['ProductID'])
#df

Making Sparse Matrix with the helpof maling pivot table along with using labelencoding

df_pivot = df.pivot_table(index='ProductID', columns='UserID', values='New_score').fillna(0)
df_pivot

UserID	0	1	2	3	4	5	6	7	8	9	...	32	33	34	35	36	37	38	39	40	41
ProductID
89	0.0	0.000000	0.000000	2.0	0.0	0.0	5.00	1.000000	2.0	0.0	...	0.000000	2.00	0.0	0.0	0.000000	3.000000	0.000000	0.000000	0.000000	3.00
333	0.0	2.000000	0.000000	0.0	0.0	3.0	0.00	0.000000	4.0	1.0	...	0.000000	1.00	3.0	0.0	0.000000	1.750000	0.000000	0.000000	0.000000	0.00
369	4.0	1.000000	0.000000	2.0	0.0	3.0	4.00	2.000000	0.0	0.0	...	0.000000	0.00	0.0	0.0	0.000000	0.000000	1.333333	0.000000	5.000000	0.00
444	2.0	2.000000	0.000000	0.0	1.0	0.0	3.00	5.000000	2.0	0.0	...	2.000000	0.00	2.5	0.0	0.000000	1.666667	0.000000	0.000000	2.666667	0.00
684	0.0	0.000000	3.000000	3.0	2.0	0.0	1.00	2.000000	2.0	0.0	...	2.500000	0.00	3.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	2.25
697	0.0	1.000000	2.000000	0.0	0.0	0.0	4.00	0.000000	1.0	2.0	...	3.000000	2.00	3.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	2.50
767	2.0	0.000000	0.000000	3.0	0.0	0.0	2.00	0.000000	0.0	0.0	...	0.000000	1.00	0.0	0.0	2.000000	0.000000	1.000000	1.000000	0.000000	0.00
777	4.0	0.000000	0.000000	0.0	0.0	0.0	1.00	0.000000	0.0	2.0	...	0.000000	1.00	0.0	0.0	0.000000	0.000000	4.000000	0.000000	0.000000	0.00
823	0.0	0.000000	0.000000	4.0	0.0	0.0	5.00	1.000000	0.0	0.0	...	0.000000	5.00	0.0	0.0	0.000000	4.000000	0.000000	0.000000	0.000000	1.50
847	0.0	0.000000	0.000000	2.0	0.0	0.0	2.00	2.333333	5.0	0.0	...	0.000000	3.00	0.0	0.0	3.000000	0.000000	0.000000	2.000000	0.000000	1.00
853	0.0	0.000000	1.000000	0.0	0.0	0.0	1.00	0.000000	0.0	0.0	...	0.000000	0.00	0.0	0.0	1.000000	0.000000	0.000000	2.000000	0.000000	0.00
858	0.0	0.000000	0.000000	0.0	2.5	0.0	3.00	2.000000	2.0	4.0	...	0.000000	0.00	0.0	0.0	0.000000	0.000000	0.000000	4.000000	0.000000	0.00
862	2.0	2.333333	0.000000	3.0	2.5	0.0	2.25	1.000000	2.5	0.0	...	1.666667	2.75	5.0	0.0	0.000000	3.200000	0.000000	0.000000	0.000000	0.00
910	0.0	2.666667	0.000000	0.0	0.0	0.0	3.00	3.000000	3.5	0.0	...	0.000000	3.00	4.0	0.0	0.000000	2.000000	0.000000	0.000000	0.000000	0.00
949	2.0	2.000000	2.000000	0.0	0.0	0.0	1.00	0.000000	3.0	0.0	...	2.000000	0.00	2.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	2.00
1002	4.0	4.000000	1.000000	0.0	0.0	0.0	1.00	0.000000	0.0	0.0	...	1.000000	0.00	2.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.00
1003	0.0	0.000000	0.000000	0.0	0.0	0.0	1.00	0.000000	2.0	0.0	...	2.000000	0.00	0.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.00
1049	2.0	3.000000	0.000000	3.0	0.0	0.0	0.00	0.000000	0.0	0.0	...	0.000000	0.00	0.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.00
1060	1.5	2.000000	1.333333	0.0	2.0	0.0	0.00	2.000000	2.0	0.0	...	2.250000	0.00	2.0	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.00
1065	0.0	0.000000	0.000000	1.0	0.0	0.0	0.00	0.000000	0.0	0.0	...	0.000000	0.00	0.0	0.0	2.500000	0.000000	0.000000	3.000000	0.000000	0.00
1077	0.0	2.000000	0.000000	2.0	1.0	0.0	1.50	1.500000	1.0	2.0	...	0.000000	0.00	0.0	0.0	1.333333	2.000000	0.000000	3.166667	0.000000	0.00
1080	0.0	2.000000	0.000000	0.0	1.0	0.0	2.00	1.000000	0.0	1.0	...	0.000000	4.00	0.0	0.0	1.000000	0.000000	0.000000	4.000000	0.000000	0.00
1095	0.0	0.000000	0.000000	1.5	3.0	0.0	0.00	1.666667	0.0	2.0	...	0.000000	0.00	0.0	4.0	0.000000	0.000000	1.500000	1.500000	3.500000	0.00
1120	0.0	0.000000	2.000000	0.0	0.0	0.0	0.00	0.000000	0.0	0.0	...	0.000000	0.00	0.0	0.0	2.000000	0.000000	0.000000	1.000000	0.000000	0.00
6969	0.0	0.000000	0.000000	0.0	0.0	0.0	0.00	0.000000	0.0	3.0	...	0.000000	3.00	0.0	0.0	0.000000	3.000000	0.000000	0.000000	0.000000	0.00
8001	0.0	2.000000	0.000000	0.0	0.0	0.0	0.00	0.000000	0.0	3.5	...	0.000000	0.00	0.0	0.0	0.000000	0.000000	2.000000	0.000000	1.000000	0.00
9696	1.0	2.000000	0.000000	2.0	0.0	0.0	1.00	2.500000	1.0	1.0	...	0.000000	2.75	0.0	0.0	0.000000	1.500000	0.000000	0.000000	0.000000	0.00

27 rows × 42 columns

Sparse Matrix (Compressed Sparse)

from scipy.sparse import csr_matrix

df_pivot_matrix = csr_matrix(df_pivot.values)
print(df_pivot_matrix)

  (0, 3)	2.0
  (0, 6)	5.0
  (0, 7)	1.0
  (0, 8)	2.0
  (0, 11)	3.0
  (0, 16)	2.5
  (0, 18)	3.0
  (0, 20)	1.0
  (0, 22)	4.0
  (0, 28)	3.0
  (0, 33)	2.0
  (0, 37)	3.0
  (0, 41)	3.0
  (1, 1)	2.0
  (1, 5)	3.0
  (1, 8)	4.0
  (1, 9)	1.0
  (1, 10)	2.0
  (1, 13)	2.0
  (1, 17)	1.25
  (1, 22)	4.0
  (1, 25)	1.25
  (1, 29)	2.5
  (1, 33)	1.0
  (1, 34)	3.0
  :	:
  (25, 17)	4.0
  (25, 21)	2.0
  (25, 22)	1.0
  (25, 25)	2.0
  (25, 30)	3.3333333333333335
  (25, 38)	2.0
  (25, 40)	1.0
  (26, 0)	1.0
  (26, 1)	2.0
  (26, 3)	2.0
  (26, 6)	1.0
  (26, 7)	2.5
  (26, 8)	1.0
  (26, 9)	1.0
  (26, 11)	2.0
  (26, 16)	2.0
  (26, 17)	1.6
  (26, 18)	2.3333333333333335
  (26, 19)	1.0
  (26, 22)	1.0
  (26, 23)	2.0
  (26, 25)	3.3333333333333335
  (26, 28)	2.0
  (26, 33)	2.75
  (26, 37)	1.5

28-06-2022

from textblob import TextBlob
from sklearn.metrics.pairwise import cosine_similarity

similarity_matrix = cosine_similarity(df_pivot)
similarity_matrix

array([[1.        , 0.34676265, 0.33723697, 0.38107647, 0.49477232,
        0.4627069 , 0.26858532, 0.26651864, 0.77150131, 0.31717595,
        0.12426828, 0.32679076, 0.48985768, 0.43446939, 0.24805411,
        0.07312724, 0.26360285, 0.0849059 , 0.17477676, 0.07714055,
        0.36102125, 0.32580206, 0.15758538, 0.        , 0.48787147,
        0.14209634, 0.6188595 ],
       [0.34676265, 1.        , 0.38234126, 0.27725706, 0.24058911,
        0.44108693, 0.17812137, 0.04713354, 0.26572428, 0.32450053,
        0.10424852, 0.18953488, 0.45902114, 0.46497647, 0.40290215,
        0.24140622, 0.16303523, 0.10010346, 0.36632991, 0.        ,
        0.21012683, 0.16645129, 0.16442598, 0.        , 0.40356568,
        0.29916176, 0.34769634],
       [0.33723697, 0.38234126, 1.        , 0.41102231, 0.15576679,
        0.35196052, 0.52867562, 0.41047143, 0.36782369, 0.34109431,
        0.13971053, 0.20874106, 0.28451058, 0.23410013, 0.22394512,
        0.33097939, 0.06519597, 0.33803328, 0.27467108, 0.02078238,
        0.33898223, 0.18037318, 0.48589697, 0.        , 0.11129753,
        0.34826045, 0.30593496],
       [0.38107647, 0.27725706, 0.41102231, 1.        , 0.62813508,
        0.51757807, 0.32052195, 0.34077389, 0.33004843, 0.41336535,
        0.42167198, 0.38264425, 0.55974449, 0.55331328, 0.607712  ,
        0.41140598, 0.25048207, 0.14474891, 0.46625563, 0.        ,
        0.52756832, 0.45944987, 0.3116387 , 0.        , 0.11961723,
        0.27108714, 0.49497036],
       [0.49477232, 0.24058911, 0.15576679, 0.62813508, 1.        ,
        0.56489663, 0.21779944, 0.20179174, 0.31660479, 0.31055744,
        0.39313159, 0.34284119, 0.52909726, 0.4205376 , 0.45651157,
        0.24160368, 0.34800801, 0.13149326, 0.43943034, 0.0568891 ,
        0.35229527, 0.25257893, 0.13504185, 0.11786218, 0.0812434 ,
        0.05239613, 0.42389844],
       [0.4627069 , 0.44108693, 0.35196052, 0.51757807, 0.56489663,
        1.        , 0.3374719 , 0.20944919, 0.54894968, 0.50589621,
        0.54157829, 0.34678732, 0.50189295, 0.49485643, 0.59931599,
        0.33679247, 0.43595531, 0.04655236, 0.3927721 , 0.16917906,
        0.36581576, 0.39361578, 0.16589032, 0.20863287, 0.29337732,
        0.21146687, 0.28769927],
       [0.26858532, 0.17812137, 0.52867562, 0.32052195, 0.21779944,
        0.3374719 , 1.        , 0.42306669, 0.42672391, 0.64658897,
        0.44328343, 0.36475482, 0.31119524, 0.21586737, 0.25855073,
        0.1721648 , 0.07399165, 0.68146193, 0.15586368, 0.38327503,
        0.66607827, 0.42450317, 0.48568076, 0.40721272, 0.08420856,
        0.2425777 , 0.26683661],
       [0.26651864, 0.04713354, 0.41047143, 0.34077389, 0.20179174,
        0.20944919, 0.42306669, 1.        , 0.23319906, 0.20041728,
        0.10827631, 0.2935387 , 0.21051075, 0.06590964, 0.19927088,
        0.35203403, 0.0244741 , 0.28050536, 0.15122737, 0.03120622,
        0.33603027, 0.35123294, 0.34137671, 0.        , 0.20054543,
        0.31136764, 0.34737312],
       [0.77150131, 0.26572428, 0.36782369, 0.33004843, 0.31660479,
        0.54894968, 0.42672391, 0.23319906, 1.        , 0.45509476,
        0.27293185, 0.26214854, 0.5268653 , 0.39301529, 0.20092067,
        0.06735267, 0.2308468 , 0.15640241, 0.05962049, 0.16239785,
        0.39003611, 0.39483518, 0.2365806 , 0.07009458, 0.5073263 ,
        0.05608952, 0.54508806],
       [0.31717595, 0.32450053, 0.34109431, 0.41336535, 0.31055744,
        0.50589621, 0.64658897, 0.20041728, 0.45509476, 1.        ,
        0.63097054, 0.38461231, 0.36049923, 0.39218556, 0.43803484,
        0.04888034, 0.29968391, 0.36653324, 0.31009315, 0.53634678,
        0.67622201, 0.53297672, 0.34672634, 0.48485711, 0.11834538,
        0.21201175, 0.29200755],
       [0.12426828, 0.10424852, 0.13971053, 0.42167198, 0.39313159,
        0.54157829, 0.44328343, 0.10827631, 0.27293185, 0.63097054,
        1.        , 0.37473303, 0.27758417, 0.40975132, 0.43061606,
        0.10398078, 0.43890054, 0.17247006, 0.13587395, 0.57082201,
        0.55913724, 0.54918159, 0.16805486, 0.56039301, 0.01598415,
        0.13401211, 0.12123435],
       [0.32679076, 0.18953488, 0.20874106, 0.38264425, 0.34284119,
        0.34678732, 0.36475482, 0.2935387 , 0.26214854, 0.38461231,
        0.37473303, 1.        , 0.3363193 , 0.35628047, 0.18325139,
        0.09828731, 0.2516869 , 0.22189711, 0.24651074, 0.28388963,
        0.5918123 , 0.51856238, 0.46243876, 0.21310118, 0.22915223,
        0.20462767, 0.3983947 ],
       [0.48985768, 0.45902114, 0.28451058, 0.55974449, 0.52909726,
        0.50189295, 0.31119524, 0.21051075, 0.5268653 , 0.36049923,
        0.27758417, 0.3363193 , 1.        , 0.79777694, 0.59505411,
        0.4518857 , 0.44505984, 0.28271758, 0.57344589, 0.19456559,
        0.458129  , 0.43234569, 0.19036497, 0.08839885, 0.37699043,
        0.24207619, 0.56021353],
       [0.43446939, 0.46497647, 0.23410013, 0.55331328, 0.4205376 ,
        0.49485643, 0.21586737, 0.06590964, 0.39301529, 0.39218556,
        0.40975132, 0.35628047, 0.79777694, 1.        , 0.6308363 ,
        0.32149781, 0.5272081 , 0.09332042, 0.53716251, 0.16351488,
        0.41563538, 0.48059499, 0.1013236 , 0.06273486, 0.38919306,
        0.41275791, 0.55455379],
       [0.24805411, 0.40290215, 0.22394512, 0.607712  , 0.45651157,
        0.59931599, 0.25855073, 0.19927088, 0.20092067, 0.43803484,
        0.43061606, 0.18325139, 0.59505411, 0.6308363 , 1.        ,
        0.49208254, 0.46849452, 0.15870628, 0.61950688, 0.16479003,
        0.41651019, 0.50257693, 0.10604121, 0.17070504, 0.12061015,
        0.4970641 , 0.26864098],
       [0.07312724, 0.24140622, 0.33097939, 0.41140598, 0.24160368,
        0.33679247, 0.1721648 , 0.35203403, 0.06735267, 0.04888034,
        0.10398078, 0.09828731, 0.4518857 , 0.32149781, 0.49208254,
        1.        , 0.13430383, 0.4397995 , 0.43421673, 0.        ,
        0.25991114, 0.18119544, 0.0587713 , 0.05913124, 0.        ,
        0.22081116, 0.26142734],
       [0.26360285, 0.16303523, 0.06519597, 0.25048207, 0.34800801,
        0.43595531, 0.07399165, 0.0244741 , 0.2308468 , 0.29968391,
        0.43890054, 0.2516869 , 0.44505984, 0.5272081 , 0.46849452,
        0.13430383, 1.        , 0.        , 0.38043379, 0.45538256,
        0.30774166, 0.35901639, 0.        , 0.2445998 , 0.14451833,
        0.18640778, 0.22069578],
       [0.0849059 , 0.10010346, 0.33803328, 0.14474891, 0.13149326,
        0.04655236, 0.68146193, 0.28050536, 0.15640241, 0.36653324,
        0.17247006, 0.22189711, 0.28271758, 0.09332042, 0.15870628,
        0.4397995 , 0.        , 1.        , 0.21412044, 0.34795214,
        0.49196503, 0.25781951, 0.30564773, 0.34327774, 0.        ,
        0.19330039, 0.32521673],
       [0.17477676, 0.36632991, 0.27467108, 0.46625563, 0.43943034,
        0.3927721 , 0.15586368, 0.15122737, 0.05962049, 0.31009315,
        0.13587395, 0.24651074, 0.57344589, 0.53716251, 0.61950688,
        0.43421673, 0.38043379, 0.21412044, 1.        , 0.09095253,
        0.342595  , 0.33258158, 0.19942638, 0.06979052, 0.12988944,
        0.34903879, 0.30579854],
       [0.07714055, 0.        , 0.02078238, 0.        , 0.0568891 ,
        0.16917906, 0.38327503, 0.03120622, 0.16239785, 0.53634678,
        0.57082201, 0.28388963, 0.19456559, 0.16351488, 0.16479003,
        0.        , 0.45538256, 0.34795214, 0.09095253, 1.        ,
        0.54114495, 0.55012884, 0.17713353, 0.8131213 , 0.07370846,
        0.09507327, 0.14070141],
       [0.36102125, 0.21012683, 0.33898223, 0.52756832, 0.35229527,
        0.36581576, 0.66607827, 0.33603027, 0.39003611, 0.67622201,
        0.55913724, 0.5918123 , 0.458129  , 0.41563538, 0.41651019,
        0.25991114, 0.30774166, 0.49196503, 0.342595  , 0.54114495,
        1.        , 0.70826251, 0.55259636, 0.41694702, 0.24452784,
        0.47836519, 0.43196319],
       [0.32580206, 0.16645129, 0.18037318, 0.45944987, 0.25257893,
        0.39361578, 0.42450317, 0.35123294, 0.39483518, 0.53297672,
        0.54918159, 0.51856238, 0.43234569, 0.48059499, 0.50257693,
        0.18119544, 0.35901639, 0.25781951, 0.33258158, 0.55012884,
        0.70826251, 1.        , 0.39620886, 0.38823622, 0.27526065,
        0.42654893, 0.48992653],
       [0.15758538, 0.16442598, 0.48589697, 0.3116387 , 0.13504185,
        0.16589032, 0.48568076, 0.34137671, 0.2365806 , 0.34672634,
        0.16805486, 0.46243876, 0.19036497, 0.1013236 , 0.10604121,
        0.0587713 , 0.        , 0.30564773, 0.19942638, 0.17713353,
        0.55259636, 0.39620886, 1.        , 0.14335282, 0.14229261,
        0.42315459, 0.36417344],
       [0.        , 0.        , 0.        , 0.        , 0.11786218,
        0.20863287, 0.40721272, 0.        , 0.07009458, 0.48485711,
        0.56039301, 0.21310118, 0.08839885, 0.06273486, 0.17070504,
        0.05913124, 0.2445998 , 0.34327774, 0.06979052, 0.8131213 ,
        0.41694702, 0.38823622, 0.14335282, 1.        , 0.        ,
        0.        , 0.        ],
       [0.48787147, 0.40356568, 0.11129753, 0.11961723, 0.0812434 ,
        0.29337732, 0.08420856, 0.20054543, 0.5073263 , 0.11834538,
        0.01598415, 0.22915223, 0.37699043, 0.38919306, 0.12061015,
        0.        , 0.14451833, 0.        , 0.12988944, 0.07370846,
        0.24452784, 0.27526065, 0.14229261, 0.        , 1.        ,
        0.4497523 , 0.57635109],
       [0.14209634, 0.29916176, 0.34826045, 0.27108714, 0.05239613,
        0.21146687, 0.2425777 , 0.31136764, 0.05608952, 0.21201175,
        0.13401211, 0.20462767, 0.24207619, 0.41275791, 0.4970641 ,
        0.22081116, 0.18640778, 0.19330039, 0.34903879, 0.09507327,
        0.47836519, 0.42654893, 0.42315459, 0.        , 0.4497523 ,
        1.        , 0.3831519 ],
       [0.6188595 , 0.34769634, 0.30593496, 0.49497036, 0.42389844,
        0.28769927, 0.26683661, 0.34737312, 0.54508806, 0.29200755,
        0.12123435, 0.3983947 , 0.56021353, 0.55455379, 0.26864098,
        0.26142734, 0.22069578, 0.32521673, 0.30579854, 0.14070141,
        0.43196319, 0.48992653, 0.36417344, 0.        , 0.57635109,
        0.3831519 , 1.        ]])

from sklearn.neighbors import NearestNeighbors

model_knn = NearestNeighbors(metric='cosine', n_neighbors=20, radius=1)
model_knn.fit(df_pivot_matrix)

NearestNeighbors(metric='cosine', n_neighbors=20, radius=1)

Pre-Processing the tweets Using reular Expression

import json

with open('D:\BB_internship_Tasks\contractions.json','r') as f:
    contractions_dict = json.load(f)
contractions = contractions_dict

def emoji(tweet):
    # Smile -- :), : ), :-), (:, ( :, (-:, :') , :O
    tweet = re.sub(r'(:\s?\)|:-\)|\(\s?:|\(-:|:\'\)|:O)', ' positiveemoji ', tweet)
    # Laugh -- :D, : D, :-D, xD, x-D, XD, X-D
    tweet = re.sub(r'(:\s?D|:-D|x-?D|X-?D)', ' positiveemoji ', tweet)
    # Love -- <3, :*
    tweet = re.sub(r'(<3|:\*)', ' positiveemoji ', tweet)
    # Wink -- ;-), ;), ;-D, ;D, (;,  (-; , @-)
    tweet = re.sub(r'(;-?\)|;-?D|\(-?;|@-\))', ' positiveemoji ', tweet)
    # Sad -- :-(, : (, :(, ):, )-:, :-/ , :-|
    tweet = re.sub(r'(:\s?\(|:-\(|\)\s?:|\)-:|:-/|:-\|)', ' negetiveemoji ', tweet)
    # Cry -- :,(, :'(, :"(
    tweet = re.sub(r'(:,\(|:\'\(|:"\()', ' negetiveemoji ', tweet)
    return tweet

import re

def process_tweet(tweet):
    tweet = tweet.lower()
    tweet = re.sub('^@[^\s]+', '', tweet)
    tweet = re.sub('((www\.[^\s]+)|(https?://[^\s]+))',' ', tweet)
    tweet = re.sub(r"\d+", " ", tweet)
    tweet = re.sub('"', " ", str(tweet))
    tweet = emoji(tweet)
    tweet = re.sub(r"\b[a-zA-Z]\b", "", str(tweet))
    for word in tweet.split():
        if word.lower() in contractions:
            tweet = tweet.replace(word, contractions[word.lower()])
    tweet = re.sub(r"[^\w\s]", " ", str(tweet))
    tweet = re.sub(r'(.)\1+', r'\1\1', tweet)
    tweet = re.sub(r"\s+", " ", str(tweet))
    return tweet

from nltk.corpus import stopwords
stop = stopwords.words('english')

def sentiments_2(text):
    try:
        return TextBlob(str(text)).sentiment.polarity
    except:
        return None
df['sentiment_2'] = df['Text'].apply(sentiments_2)
df

	ProductID	UserID	Rating	Text	sentiment	Updated_score	New_score	sentiment_2
0	777	0	4	Great taffy at a great price.	0.800000	3.200000	4	0.800000
1	767	3	4	Absolutely wonderful - silky and sexy and comf...	0.633333	2.533333	3	0.633333
2	1080	13	5	Love this dress! it's sooo pretty.	0.437500	2.187500	3	0.437500
3	1077	3	3	I had such high hopes for this dress and reall...	0.120000	0.360000	2	0.120000
4	1049	3	5	I love, love, love this jumpsuit. it's fun, fl...	0.550000	2.750000	3	0.550000
...	...	...	...	...	...	...	...	...
629	823	41	1	I placed order 4+1 soaps.But I have received w...	0.000000	0.000000	1	0.000000
630	823	41	3	The soap is ok for bathing, no scent at all, m...	0.325000	0.975000	2	0.325000
631	847	41	5	For a long time I was searching for Indian soa...	-0.025000	-0.125000	1	-0.025000
632	910	7	3	Good but not great	0.150000	0.450000	2	0.150000
633	333	13	5	Quick,easy to make & tasty too.	0.000000	0.000000	1	0.000000

634 rows × 8 columns

df['processed_text'] = df['Text'].apply(process_tweet)
#df['processed_text'] = df['processed_text'].apply
df

	ProductID	UserID	Rating	Text	sentiment	Updated_score	New_score	sentiment_2	processed_text
0	777	0	4	Great taffy at a great price.	0.800000	3.200000	4	0.800000	great taffy at great price
1	767	3	4	Absolutely wonderful - silky and sexy and comf...	0.633333	2.533333	3	0.633333	absolutely wonderful silky and sexy and comfor...
2	1080	13	5	Love this dress! it's sooo pretty.	0.437500	2.187500	3	0.437500	love this dress it soo pretty
3	1077	3	3	I had such high hopes for this dress and reall...	0.120000	0.360000	2	0.120000	had such high hopes for this dress and really...
4	1049	3	5	I love, love, love this jumpsuit. it's fun, fl...	0.550000	2.750000	3	0.550000	love love love this jumpsuit it fun flirty an...
...	...	...	...	...	...	...	...	...	...
629	823	41	1	I placed order 4+1 soaps.But I have received w...	0.000000	0.000000	1	0.000000	placed order soaps but have received without ...
630	823	41	3	The soap is ok for bathing, no scent at all, m...	0.325000	0.975000	2	0.325000	the soap is ok for bathing no scent at all mor...
631	847	41	5	For a long time I was searching for Indian soa...	-0.025000	-0.125000	1	-0.025000	for long time was searching for indian soap eq...
632	910	7	3	Good but not great	0.150000	0.450000	2	0.150000	good but not great
633	333	13	5	Quick,easy to make & tasty too.	0.000000	0.000000	1	0.000000	quick easy to make tasty too

634 rows × 9 columns

4-7-2022 Here we will find data/nearest data

product_ID = int(input('Enter Product Id: '))
data = df_pivot.index.to_list()
data

Enter Product Id: 369

[89,
 333,
 369,
 444,
 684,
 697,
 767,
 777,
 823,
 847,
 853,
 858,
 862,
 910,
 949,
 1002,
 1003,
 1049,
 1060,
 1065,
 1077,
 1080,
 1095,
 1120,
 6969,
 8001,
 9696]

query_index = data.index(product_ID)
print(query_index)

2

distance, indices = model_knn.kneighbors(df_pivot.iloc[query_index,:].values.reshape(1,-1), n_neighbors = 8)
print(distance)
print(indices)

[[0.         0.47132438 0.51410303 0.58897769 0.58952857 0.61765874
  0.63217631 0.64803948]]
[[ 2  6 22  3  7  1  8  5]]

f=df_pivot.index[indices.flatten()]
f

Int64Index([369, 767, 1095, 444, 777, 333, 823, 697], dtype='int64', name='ProductID')

#import pandas as pd
#x=pd.DataFrame(df_pivot.index(f))
#x

#Presenting data in tablular format...

p_id = int(input('Enter product id: '))
data = df_pivot.index.to_list()
query_index = data.index(p_id)

distance, indices = model_knn.kneighbors(df_pivot.iloc[query_index,:].values.reshape(1,-1), n_neighbors = 8)
#print(distance)
#print(indices)
x=pd.DataFrame(df_pivot.index[indices.flatten()])
x.drop(0)                         #here the first row should not be displayed so

Enter product id: 369

	ProductID
1	767
2	1095
3	444
4	777
5	333
6	823
7	697

print(type(distance))

<class 'numpy.ndarray'>

distance.tolist(), indices.tolist()

([[0.0,
   0.4713243830572561,
   0.5141030253286081,
   0.5889776911252591,
   0.5895285707784645,
   0.6176587445860691,
   0.6321763125811057,
   0.6480394832572696]],
 [[2, 6, 22, 3, 7, 1, 8, 5]])

list(zip(distance.tolist()[0], indices.tolist()[0]))

[(0.0, 2),
 (0.4713243830572561, 6),
 (0.5141030253286081, 22),
 (0.5889776911252591, 3),
 (0.5895285707784645, 7),
 (0.6176587445860691, 1),
 (0.6321763125811057, 8),
 (0.6480394832572696, 5)]

val= list(df['sentiment_2'].values)
netural=0
negative=0
positive=0
for i in val:
    
    if i > 0:
        positive += 1
    elif i < 0:
        negative += 1
    else:
        netural += 1
    
print('Neutrals', netural)
print('Positive', positive)
print('Negative', negative)

Neutrals 85
Positive 451
Negative 98

import matplotlib.pyplot as plt
import numpy as np

p= np.array([netural,positive,negative])
mylabel=['Neutral',' Positive', 'Negative']
shad = [0.3,0.3,0.4]
plt.pie(p, labels=mylabel, explode=shad, shadow= True, autopct ="%2.1f")
plt.show()

#vals = df['Rating'].value_counts().tolist()
#labs = df['Rating'].unique().tolist()
#plt.bar(labs, vals)
#plt.xlabel("Rating")
#plt.ylabel("No. Of Reviews")
#plt.show()
#vals

one=0
two=0
three=0
four=0
five=0
zero=0
vals = list(df['Rating'].values)

for i in vals:
    if i == 0:
        zero += 1
    elif i == 1:
        one += 1
    elif i == 2:
        two += 1
    elif i == 3:
        three += 1
    elif i == 4:
        four += 1
    elif i == 5:
        five += 1

print('0 Rating', zero)
print('1 Rating', one)
print('2 Rating', two)
print('3 Rating', three)
print('4 Rating', four)
print('5 Rating', five)

0 Rating 1
1 Rating 125
2 Rating 34
3 Rating 48
4 Rating 86
5 Rating 340

x_rating = np.array([0,1,2,3,4,5])
y_review = np.array([zero,one,two,three,four,five])
plt.bar(x_rating,y_review, width=0.5, color='yellow')
plt.xlabel("Rating from 0-5")
plt.ylabel("No. of Review")
plt.show()