pip install xlrd

Requirement already satisfied: xlrd in /usr/local/lib/python3.7/site-packages (2.0.1)
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
Note: you may need to restart the kernel to use updated packages.

pip install openpyxl

Requirement already satisfied: openpyxl in /usr/local/lib/python3.7/site-packages (3.0.9)
Requirement already satisfied: et-xmlfile in /usr/local/lib/python3.7/site-packages (from openpyxl) (1.1.0)
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
Note: you may need to restart the kernel to use updated packages.

pip install --upgrade pip

Requirement already satisfied: pip in /usr/local/lib/python3.7/site-packages (22.0.4)
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
Note: you may need to restart the kernel to use updated packages.

import pandas as pd import xlrd as xlrd import matplotlib.pyplot as plt movies = pd.read_csv("Movies_dataset.csv", sep=",")

movies.info

movies.head(5)

tconstobject

titleTypeobject

tt0000001

short

tt0000002

short

tt0000003

short

tt0000004

short

tt0000005

short

1.

print(movies)

             tconst  titleType            primaryTitle  startYear  \
0         tt0000001      short              Carmencita     1894.0   
1         tt0000002      short  Le clown et ses chiens     1892.0   
2         tt0000003      short          Pauvre Pierrot     1892.0   
3         tt0000004      short             Un bon bock     1892.0   
4         tt0000005      short        Blacksmith Scene     1893.0   
...             ...        ...                     ...        ...   
2158087  tt12806064  tvEpisode            Peacefulness     2019.0   
2158088  tt12806066  tvEpisode         Episode #1.7811     1996.0   
2158089  tt12806068      movie           Royals at War     2020.0   
2158090   tt1280606  tvEpisode        Falsche Diagnose     1999.0   
2158091  tt12806070  tvEpisode                  Episod        NaN   

         runtimeMinutes                    genres  averageRating  numVotes  
0                   1.0         Documentary,Short            5.7    1869.0  
1                   5.0           Animation,Short            5.9     247.0  
2                   4.0  Animation,Comedy,Romance            6.5    1641.0  
3                  12.0           Animation,Short            5.8     159.0  
4                   1.0              Comedy,Short            6.2    2466.0  
...                 ...                       ...            ...       ...  
2158087             NaN   Animation,Comedy,Family            NaN       NaN  
2158088             NaN             Drama,Romance            NaN       NaN  
2158089           102.0               Documentary            7.1      40.0  
2158090            46.0               Crime,Drama            NaN       NaN  
2158091             NaN                       NaN            NaN       NaN  

[2158092 rows x 8 columns]

2.

2.1 Filtering "titleType" nach "movie" und "tvMovie"

movies.value_counts("titleType")

movies.loc[(movies["titleType"]).str.contains("movie")]

tconstobject

titleTypeobject

498

tt0000502

movie

570

tt0000574

movie

587

tt0000591

movie

610

tt0000615

movie

625

tt0000630

movie

668

tt0000675

movie

672

tt0000679

movie

729

tt0000739

movie

783

tt0000793

movie

804

tt0000814

movie

movies.loc[(movies["titleType"]).str.contains("movie") | (movies["titleType"]).str.contains("tvMovie")]

tconstobject

titleTypeobject

498

tt0000502

movie

570

tt0000574

movie

587

tt0000591

movie

610

tt0000615

movie

625

tt0000630

movie

668

tt0000675

movie

672

tt0000679

movie

729

tt0000739

movie

783

tt0000793

movie

804

tt0000814

movie

#Variable movies_restricted_1 mit Filter movies_restricted_1=movies.loc[(movies["titleType"]).str.contains("movie") | (movies["titleType"]).str.contains("tvMovie")]

print(movies_restricted_1)

             tconst titleType                          primaryTitle  \
498       tt0000502     movie                              Bohemios   
570       tt0000574     movie           The Story of the Kelly Gang   
587       tt0000591     movie                      The Prodigal Son   
610       tt0000615     movie                    Robbery Under Arms   
625       tt0000630     movie                                Hamlet   
...             ...       ...                                   ...   
2157912  tt12805730     movie                               T h e m   
2157942  tt12805782     movie  Leopards: The Ghosts of the Savannah   
2157981  tt12805862     movie                                 Eynak   
2157985  tt12805870     movie                         Rhino Express   
2158089  tt12806068     movie                         Royals at War   

         startYear  runtimeMinutes                      genres  averageRating  \
498         1905.0           100.0                         NaN            4.5   
570         1906.0            70.0  Action,Adventure,Biography            6.0   
587         1907.0            90.0                       Drama            4.6   
610         1907.0             NaN                       Drama            4.5   
625         1908.0             NaN                       Drama            3.8   
...            ...             ...                         ...            ...   
2157912     2021.0            84.0             Sci-Fi,Thriller            7.3   
2157942     2020.0            52.0                 Documentary            NaN   
2157981     1987.0            55.0                         NaN            NaN   
2157985     2022.0           129.0                      Comedy            8.6   
2158089     2020.0           102.0                 Documentary            7.1   

         numVotes  
498          14.0  
570         758.0  
587          17.0  
610          23.0  
625          24.0  
...           ...  
2157912      27.0  
2157942       NaN  
2157981       NaN  
2157985      29.0  
2158089      40.0  

[329966 rows x 8 columns]

movies_restricted_1.head(10)

tconstobject

tt000050210%

tt000057410%

8 others80%

titleTypeobject

movie100%

498

tt0000502

movie

570

tt0000574

movie

587

tt0000591

movie

610

tt0000615

movie

625

tt0000630

movie

668

tt0000675

movie

672

tt0000679

movie

729

tt0000739

movie

783

tt0000793

movie

804

tt0000814

movie

movies_restricted_1.loc[(movies_restricted_1["startYear"]>=1980)]

tconstobject

titleTypeobject

11636

tt0011801

movie

15179

tt0015414

movie

15487

tt0015724

movie

25101

tt0025541

movie

34805

tt0035423

movie

35969

tt0036606

movie

38013

tt0038687

movie

53245

tt0054261

tvMovie

56375

tt0057461

movie

58205

tt0059325

movie

movies_restricted_2: Anwendung Filter > 1980

#Variable movies_restricted_2 mit Filter > 1980 movies_restricted_2=movies_restricted_1.loc[(movies_restricted_1["startYear"]>=1980)]

movies_restricted_2.sort_values(by=["startYear"])

tconstobject

titleTypeobject

189312

tt0211238

movie

270945

tt0302601

tvMovie

437871

tt0491983

movie

184947

tt0206386

movie

860602

tt0934859

tvMovie

143014

tt0156126

movie

214730

tt0239307

movie

143042

tt0156158

movie

143046

tt0156162

movie

214757

tt0239336

movie

2.3 Exclude rows with missing ratings or genres

#leere_Werte_genres = movies_restricted_2.isna()

#leere_Werte_genres = movies_restricted_2["genres"].isna()

#print(leere_Werte_genres)

#leere_Werte_rating = movies_restricted_2["averageRating"].isna()

leere_Werte_genres = movies_restricted_2["genres"].isna()==False

leere_Werte_rating = movies_restricted_2["averageRating"].isna()==False

#Variable movies_restricted_3 movies_restricted_3=movies_restricted_2[leere_Werte_genres & leere_Werte_rating]

movies_restricted_3.head(8)

tconstobject

titleTypeobject

15487

tt0015724

movie

34805

tt0035423

movie

35969

tt0036606

movie

38013

tt0038687

movie

56375

tt0057461

movie

58205

tt0059325

movie

58759

tt0059900

movie

60971

tt0062181

movie

3.

movies_restricted_4=movies_restricted_3.groupby("startYear")["averageRating"].mean().reset_index().round(decimals=2)

movies_restricted_4.plot.scatter(x = "startYear", y = "averageRating") #plt.title("Diameter/Price") #plt.show()

4.

4.1 Ratings

movies_restricted_3[["tconst", "averageRating"]]

tconstobject

averageRatingfloat64

15487

tt0015724

6.2

34805

tt0035423

6.4

35969

tt0036606

6.5

38013

tt0038687

7.4

56375

tt0057461

4.9

58205

tt0059325

6.4

58759

tt0059900

6.7

60971

tt0062181

6.5

61117

tt0062336

6.4

61610

tt0062842

6.6

ratings=movies_restricted_3[["tconst", "averageRating"]]

ratings.to_csv("ratings.csv")

4.2 Titles

movies_restricted_3[["tconst", "primaryTitle", "startYear", "runtimeMinutes", "genres"]]

tconstobject

primaryTitleobject

15487

tt0015724

Dama de noche

34805

tt0035423

Kate & Leopold

35969

tt0036606

Another Time, Another Place

38013

tt0038687

Let There Be Light

56375

tt0057461

La rosa de los vientos

58205

tt0059325

Born in '45

58759

tt0059900

Wenn du groß bist, lieber Adam

60971

tt0062181

Rece do góry

61117

tt0062336

The Tango of the Widower and Its Distorting Mirror

61610

tt0062842

Cuore di mamma

title=movies_restricted_3[["tconst", "primaryTitle", "startYear", "runtimeMinutes", "genres"]]

title.to_csv("title.csv")

1.

2.

2.1 Filtering "titleType" nach "movie" und "tvMovie"

movies_restricted_2: Anwendung Filter &gt; 1980

2.3 Exclude rows with missing ratings or genres

3.

4.

4.1 Ratings

4.2 Titles

movies_restricted_2: Anwendung Filter > 1980