Parte 5 Biblioteca Pandas

import pandas as pd

carros = ['Jetta Variant','Passat','CrossFox']
carros

pd.Series(carros)

datos = [
    {'Nombre': 'Jetta Variant', 'Motor': 'Motor 4.0 Turbo', 'Año': 2003, 'Kilometraje': 44410.0, 'Cero_km': False, 'Valor': 88078.64},
    {'Nombre': 'Passat', 'Motor': 'Motor Diesel', 'Año': 1991, 'Kilometraje': 5712.0, 'Cero_km': False, 'Valor': 106161.94},
    {'Nombre': 'Crossfox', 'Motor': 'Motor Diesel V8', 'Año': 1990, 'Kilometraje': 37123.0, 'Cero_km': False, 'Valor': 72832.16}
]

dataset = pd.DataFrame(datos)

dataset

dataset[['Nombre','Año','Motor','Kilometraje','Cero_km','Valor']]

datos = {
    'Nombre': ['Jetta Variant', 'Passat', 'Crossfox'], 
    'Motor': ['Motor 4.0 Turbo', 'Motor Diesel', 'Motor Diesel V8'],
    'Año': [2003, 1991, 1990],
    'Kilometraje': [44410.0, 5712.0, 37123.0],
    'Cero_km': [False, False, False],
    'Valor': [88078.64, 106161.94, 72832.16]

dataset1 =pd.DataFrame(datos)

dataset1

dataset2 = pd.read_csv('db.csv',sep =';',index_col = 0)

dataset2

dataset2.head()

dataset2['Valor']

type(dataset2['Valor'])

dataset2[['Valor']]

type(dataset2[['Valor']])

dataset2[0:3]

dataset2.loc['Passat']

dataset2.loc[['Passat','DS5']]

dataset2.loc[['Passat','DS5'],['Motor','Valor']]

dataset2.loc[:,['Motor','Valor']]

dataset2.head()

dataset2.iloc[[1]]

dataset2.iloc[1:4]

dataset2.iloc[1:4,[0,5,2]]

dataset2.iloc[[1,42,22],[0,5,2]]

dataset2.iloc[:,[0,5,2]]

dataset2.head()

dataset2.Motor

dataset2.Motor == 'Motor Diesel'

type(dataset2.Motor == 'Motor Diesel')

dataset2[dataset2.Motor == 'Motor Diesel']

dataset2[(dataset2.Motor == 'Motor Diesel') & (dataset2.Cero_km == True)]

dataset2.query('Motor == "Motor Diesel" and Cero_km == True')

dataset2.head()

for item in dataset2:
  print(item)

list(dataset2.iterrows())

for index,row in dataset2.iterrows():
  if(2020 - row.Año != 0):
    dataset2.loc[index,'km_average'] = row.Kilometraje / (2020 - row.Año)
  else:
    dataset2.loc[index,'km_average'] = 0

dataset2

dataset2.head()

dataset2.info()

dataset2.Kilometraje.isna()

dataset2[dataset2.Kilometraje.isna()]

dataset2.fillna(0)

dataset2

dataset2.fillna(0,inplace = True)

dataset2

dataset2.query('Cero_km == True')

dataset3 = pd.read_csv('db.csv',sep = ';')

dataset3

dataset3.dropna(subset = ['Kilometraje'],inplace = True)

dataset3