# Vamos a crear una estructura de serie
import pandas as pd
serie= pd.Series(data=[1,2,3,4],index=['David','Juan',1,2],name='SerieX')
serie

# Algunas propiedades de la serie
print('Indice de la serie:',serie.index)
print('Valores de la serie:',serie.values)
print('Longitud de serie:',serie.count())
# Verificar nulos en la serie
serie.isna()

# Filtrar un indice
serie.loc['David']

# Filtrar pero de otra forma
serie.iloc[0]

# Filtrar varios indices
serie.loc[['David',1]]

import numpy as np
serie_2= pd.Series(data=[1,2,5,6,np.nan , 20,np.nan])
serie_2

# Suma de nulos
serie_2.isnull().sum()

# Conteo de valores no tiene en cuenta los NaN
serie_2.value_counts()

# Creemos un dataframe
valores= [1000, 3500, 3000, 4000, 3000 , 2450]
nombres= ['David','Juan','Pedro','Lucas','Andrea','Felipe']
genero=['M','M','M','M','F','M']
df= pd.DataFrame(data={'salarios':valores, 'genero':genero},index=nombres)
df

# filtremos por genero
df_m= df[df['genero']=='M']
print(df_m.head())
print('------')
df_f=df[df['genero']=='F']
print(df_f.head())

# Otra forma
condicion_h = df['genero']=='M'
condicion_m = df['genero']=='F'
print(df[condicion_h])
print('-------------')
print(df[condicion_m])

# Algunas cosas adicionales
df.loc['David'][['salarios','genero']]

df.loc[['David','Juan']][['salarios','genero']]

from google.colab import drive
import os
drive.mount('/content/gdrive')

%cd '/content/gdrive/MyDrive'
df= pd.read_csv('winequality-red.csv',sep=',')
print(df[['density','pH','sulphates','alcohol','quality']].head())

%cd '/content/gdrive/MyDrive'
df= pd.read_csv('pokemon_data.txt',delimiter='\t')
print(df[['Name','Type 1','HP','Attack','Defense']].head())

%cd '/content/gdrive/MyDrive'
df= pd.read_excel('defaultoutput.xlsx')
print(df[['index','ID','Year_Birth','Education','Income']].head())

import pandas as pd

url = 'https://raw.githubusercontent.com/JJTorresDS/stocks-ds-edu/main/stocks.csv'
df = pd.read_csv(url, index_col=0)
print(df[['AMZN','MCD','SBUX','GOOG','MSFT']].head(5).round(1))

!wget -O cars_clus.csv https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/ML0101ENv3/labs/cars_clus.csv

filename = 'cars_clus.csv'
#Lectura
pdf = pd.read_csv(filename)
print ("Shape: ", pdf.shape)
print(pdf[['manufact','model','sales','resale']].head(5))

import pandas as pd

url = 'https://raw.githubusercontent.com/JJTorresDS/stocks-ds-edu/main/stocks.csv'
df = pd.read_csv(url, index_col=0)
print(df.head(5))

df.head()

df.shape

df['MCD'].plot(kind='line',figsize=(10,6),xlabel='Fecha', ylabel='Precio Accion', title='Precio Accion vs Fecha')

df.plot(kind='line',figsize=(15,6),xlabel='Fecha', ylabel='Precio Accion', title='Precio Accion vs Fecha').legend(loc='best')

df_cambios=df.pct_change()*100
df_cambios

df_cambios.plot(kind='line',figsize=(15,6),xlabel='Fecha', ylabel='Porcentaje de cambio', title='Precio Accion vs Fecha').legend(loc='best')

df_n=df.copy()
df_n['Fecha']=df.index
df_n= df_n.reset_index(drop=True)
df_n

df_long=pd.melt(df_n , value_vars=df.columns,id_vars='Fecha')
df_long

import plotly.express as px


fig=px.line(data_frame=df_long,x='Fecha',y='value',line_group='variable',color='variable',title='Comportamiento de precio de acciones',\
             labels={
                     "Fecha": "Fecha_dias",
                     "value": "Precio (USD)"
                 })
fig.update_layout(paper_bgcolor="#FFFFFF",plot_bgcolor='#FFFFFF',)

fig.show()

df_n=df.copy()
df_n['Fecha']=df.index
df_n= df_n.reset_index(drop=True)
df_n= df_n.drop(columns=['GOOG','AMZN'])
df_n

columnas=list(df.columns)
unwanted_num = {'AMZN', 'GOOG'}
 
col_final = [x for x in columnas if x not in unwanted_num]
col_final

df_long=pd.melt(df_n , value_vars=col_final,id_vars='Fecha')
df_long

import plotly.express as px


fig=px.line(data_frame=df_long,x='Fecha',y='value',line_group='variable',color='variable',title='Comportamiento de precio de acciones',\
             labels={
                     "Fecha": "Fecha_dias",
                     "value": "Precio (USD)"
                 })
fig.update_layout(paper_bgcolor="#FFFFFF",plot_bgcolor='#FFFFFF',)

fig.show()