Rating_Prediction/data_load.py at master · C-Ritam98/Rating_Prediction · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

import numpy as np
import matplotlib.pyplot as plt
import os
import csv
import pandas as pd

files = os.listdir()

file_name = "combined_data_"


#Reading reviews from file


with open(file_name + "1." + "txt",'r') as f:
          lines = f.read().split('\n')

reviews = []
movie_id = 0
new_row = []
lines = lines[:-1]

with open("train_data.csv",'w') as f:

    writer = csv.writer(f)
    writer.writerow(["Movie_Id","Person_Id","Rating"])

    for line in lines:
        if len(line)==0:
            continue
        if(line[-1] == ':'):
            #print(movie_id)
            movie_id += 1
            continue
        new_row = [movie_id] + line.split(',')[:-1]
        new_row[1] = int(new_row[1])
        if new_row[1]>10000:
            continue
        new_row[2] = int(new_row[2])
        #reviews.append(new_row)
        writer.writerow(new_row)

with open(file_name + "2." + "txt",'r') as f:
          lines = f.read().split('\n')

reviews = []
new_row = []
lines = lines[:-1]

with open("train_data.csv",'w') as f:

    writer = csv.writer(f)
    writer.writerow(["Movie_Id","Person_Id","Rating"])

    for line in lines:
        if len(line)==0:
            continue
        if(line[-1] == ':'):
            #print(movie_id)
            movie_id += 1
            continue
        new_row = [movie_id] + line.split(',')[:-1]
        new_row[1] = int(new_row[1])
        if new_row[1]>10000:
            continue
        new_row[2] = int(new_row[2])
        #reviews.append(new_row)
        writer.writerow(new_row)