import pandas as pd
import numpy as np
import re #Modulo de Expresiones Regulares
moviesDf = pd.read_csv('movies_dataset.csv', sep=',')
/shared-libs/python3.9/py-core/lib/python3.9/site-packages/IPython/core/interactiveshell.py:3139: DtypeWarning: Columns (10) have mixed types.Specify dtype option on import or set low_memory=False.
has_raised = await self.run_ast_nodes(code_ast.body, cell_name,
#Verificamos el dataset moviesDf
moviesDf.head()
adultobject
belongs_to_collectionobject
0
False
{'id': 10194, 'name': 'Toy Story Collection', 'poster_path': '/7G9915LfUQ2lVfwMEEhDsn3kT4B.jpg', 'backdrop_path': '/9FBwqcd9IRruEDUrTdcaafOMKUq.jpg'}
1
False
nan
2
False
{'id': 119050, 'name': 'Grumpy Old Men Collection', 'poster_path': '/nLvUdqgPgm3F85NMCii9gVFUcet.jpg', 'backdrop_path': '/hypTnLot2z8wpFS7qwsQHW1uV8u.jpg'}
3
False
nan
4
False
{'id': 96871, 'name': 'Father of the Bride Collection', 'poster_path': '/nts4iOmNnq7GNicycMJ9pSAn204.jpg', 'backdrop_path': '/7qwE57OVZmMJChBpLEbJEmzUydk.jpg'}
moviesDf.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 45466 entries, 0 to 45465
Data columns (total 24 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 adult 45466 non-null object
1 belongs_to_collection 4494 non-null object
2 budget 45466 non-null object
3 genres 45466 non-null object
4 homepage 7782 non-null object
5 id 45466 non-null object
6 imdb_id 45449 non-null object
7 original_language 45455 non-null object
8 original_title 45466 non-null object
9 overview 44512 non-null object
10 popularity 45461 non-null object
11 poster_path 45080 non-null object
12 production_companies 45463 non-null object
13 production_countries 45463 non-null object
14 release_date 45379 non-null object
15 revenue 45460 non-null float64
16 runtime 45203 non-null float64
17 spoken_languages 45460 non-null object
18 status 45379 non-null object
19 tagline 20412 non-null object
20 title 45460 non-null object
21 video 45460 non-null object
22 vote_average 45460 non-null float64
23 vote_count 45460 non-null float64
dtypes: float64(4), object(20)
memory usage: 8.3+ MB
#Función para extraer y concatenar 'name'
def extract_concatenate_name(value):
try:
pattern = r"'name':\s+'(.*?)'"
match = re.findall(pattern, value)
return ', '.join(match)
except (TypeError, AttributeError):
return ''
#Normalizamos la columna "belongs_to_collection"
moviesDf['collection'] = moviesDf['belongs_to_collection'].apply(extract_concatenate_name)
moviesDf['collection'].head(10)
#Normalizamos la columna "genres"
moviesDf['genre'] = moviesDf['genres'].apply(extract_concatenate_name)
moviesDf['genre'].head(10)
#Normalizamos la columna la columna "production_companies"
moviesDf['company'] = moviesDf['production_companies'].apply(extract_concatenate_name)
moviesDf['company'].head(10)
#Normalizamos la columna "production_countries"
moviesDf['country'] = moviesDf['production_countries'].apply(extract_concatenate_name)
moviesDf['country'].head(10)
#Normalizamos la columna "spoken_languages"
moviesDf['language'] = moviesDf['spoken_languages'].apply(extract_concatenate_name)
moviesDf['language'].head(10)
moviesDf.head(0)
adultobject
belongs_to_collectionobject
moviesDf['budget'].fillna(0, inplace=True)
print('# de valores NULL en el campo budget:', moviesDf.budget.isna().sum())
# de valores NULL en el campo budget: 0
moviesDf['revenue'].fillna(0, inplace=True)
print('# de valores NULL en el campo revenue:', moviesDf.revenue.isna().sum())
# de valores NULL en el campo revenue: 0
#Damos formato a todos los valores de la columna 'release_date'
#A los que no se les puede dar formato se les asigna NaT (Not a Time)
moviesDf['release_date'] = pd.to_datetime(moviesDf['release_date'], errors='coerce')
#Eliminamos los registros NaT
moviesDf.dropna(subset = ['release_date'], inplace=True)
#Verificamor que no existan NaT
moviesDf['release_date'].isnull().sum()
#Verificamos que todos los registros tengan el mismo formato AAAA-MM-DD
moviesDf['release_date'] = pd.to_datetime(moviesDf['release_date']).dt.strftime('%Y-%m-%d')
#Creamos la columna 'release_year' que va a contener el año de la columna 'release_date'
moviesDf['release_year'] = pd.to_datetime(moviesDf['release_date']).dt.year
#Verificamos las columnas 'release_date','release_year'
moviesDf[['release_date','release_year']].tail()
release_dateobject
release_yearint64
45460
1991-05-13
1991
45462
2011-11-17
2011
45463
2003-08-01
2003
45464
1917-10-21
1917
45465
2017-06-09
2017
#Damos formato a los registros de las columnas 'budget' y 'revenue' a tipo numerico
#A los que no se les puede dar formato se les asigna el valor NaN (Not a Number)
moviesDf['budget'] = pd.to_numeric(moviesDf['budget'], errors='coerce')
moviesDf['revenue'] = pd.to_numeric(moviesDf['revenue'], errors='coerce')
#Realizamos el calculo del retorno de inversión 'return'
moviesDf['return'] = moviesDf['revenue']/moviesDf['budget']
moviesDf['return'].fillna(0, inplace=True)
#moviesDf.drop(columns=['video', 'imdb_id', 'adult', 'original_title', 'vote_count', 'poster_path', 'homepage'], inplace = True)
moviesDf = moviesDf[['id', 'title', 'tagline', 'overview', 'runtime',
'original_language', 'genre', 'collection',
'status', 'release_date', 'release_year',
'popularity','vote_average',
'company', 'country', 'language',
'revenue', 'budget', 'return']]
moviesDf.head()
idobject
titleobject
0
862
Toy Story
1
8844
Jumanji
2
15602
Grumpier Old Men
3
31357
Waiting to Exhale
4
11862
Father of the Bride Part II
movie_listing = moviesDf.to_csv('movie_listing.csv', index=False, header=True, sep=';')