10 KiB
10 KiB
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inlinedf_movie = pd.read_csv('movies.dat',sep='::',encoding='latin1',engine='python',names=['MovieID','MovieName','Category'])
df_movie.dropna(inplace=True)
df_movie.head()| MovieID | MovieName | Category | |
|---|---|---|---|
| 0 | 1 | Toy Story (1995) | Animation|Children's|Comedy |
| 1 | 2 | Jumanji (1995) | Adventure|Children's|Fantasy |
| 2 | 3 | Grumpier Old Men (1995) | Comedy|Romance |
| 3 | 4 | Waiting to Exhale (1995) | Comedy|Drama |
| 4 | 5 | Father of the Bride Part II (1995) | Comedy |
df_rating = pd.read_csv('ratings.dat',sep='::',encoding='latin1',engine='python',names=['ID','MovieID','Ratings','TimeStamp'])
df_rating.dropna(inplace=True)
df_rating.head()| ID | MovieID | Ratings | TimeStamp | |
|---|---|---|---|---|
| 0 | 1 | 1193 | 5 | 978300760 |
| 1 | 1 | 661 | 3 | 978302109 |
| 2 | 1 | 914 | 3 | 978301968 |
| 3 | 1 | 3408 | 4 | 978300275 |
| 4 | 1 | 2355 | 5 | 978824291 |
df = pd.merge(df_movie,df_rating,left_on='MovieID',right_on='MovieID')
df.head()| MovieID | MovieName | Category | ID | Ratings | TimeStamp | |
|---|---|---|---|---|---|---|
| 0 | 1 | Toy Story (1995) | Animation|Children's|Comedy | 1 | 5 | 978824268 |
| 1 | 1 | Toy Story (1995) | Animation|Children's|Comedy | 6 | 4 | 978237008 |
| 2 | 1 | Toy Story (1995) | Animation|Children's|Comedy | 8 | 4 | 978233496 |
| 3 | 1 | Toy Story (1995) | Animation|Children's|Comedy | 9 | 5 | 978225952 |
| 4 | 1 | Toy Story (1995) | Animation|Children's|Comedy | 10 | 5 | 978226474 |
groupByMovie = df.groupby('MovieID')
movieRatingsMean = groupByMovie['Ratings'].mean()*2
movieRatingsMean.columns = ['MovieID','Mean']
movieRatingsMeanMovieID
1 8.293693
2 6.402282
3 6.033473
4 5.458824
5 6.013514
...
3948 7.271462
3949 8.230263
3950 7.333333
3951 7.800000
3952 7.561856
Name: Ratings, Length: 3706, dtype: float64