#Llamamos el set de datos público zoo_data = 'https://archive.ics.uci.edu/ml/machine-learning-databases/zoo/zoo.data' # los nombres de las columnas se encuentran en : 'https://archive.ics.uci.edu/ml/machine-learning-databases/zoo/zoo.names' zoo_name= ['animal name','hair','feathers','eggs','milk','airborne','aquatic','predator','toothed','backbone','breathes','venomous','fins','legs','tail','domestic',' cat-size','type']

import pandas as pd

data= pd.read_csv(zoo_data)

data.head()

data.columns=zoo_name

data.head()

#librerias de graficación más empleadas import plotly as plt import seaborn as sns

import altair as alt # gráfica

plot_01=alt.Chart(data).mark_line().encode( x='animal name', y='legs' )

plot_01

plot_02=alt.Chart(data).mark_bar().encode( x='animal name', y='legs' )

plot_02

import plotly.express as px

fig = px.pie(data, values='aquatic', names='animal name', title='Porcentaje de animales acuáticos') # gráfica de pie fig.show()

#Llamamos el set de datos público Chicago_data = 'https://raw.githubusercontent.com/terranigmark/curso-analisis-exploratorio-datos-platzi/main/Traffic_Crashes1.csv' token_map_plot='pk.eyJ1IjoiY2hlbWlza3kiLCJhIjoiY2tnOGNhcXk3MGZ3eDJ5b2FxZ3ViajN1MyJ9.t3R24lWTwzTQwyJw4vuWFw'

import pandas as pd

Chicago_df=pd.read_csv(Chicago_data) Chicago_df

Chicago_df.head()

Chicago_df.info()

Chicago_df['CRASH_DATE']=Chicago_df['CRASH_DATE'].apply(lambda x: pd.to_datetime(x,errors='coerce',utc=True))

Chicago_df.info()

Chicago_df['NUM_UNITS'] = Chicago_df['NUM_UNITS'].astype('int32')

import plotly.express as px px.set_mapbox_access_token(token_map_plot)

px.scatter_mapbox(Chicago_df,lat='LATITUDE',lon='LONGITUDE',color='CRASH_HOUR',size='NUM_UNITS', color_continuous_scale=px.colors.cyclical.IceFire,zoom=10)

#Llamamos el set de datos público Chicago_data = 'https://raw.githubusercontent.com/terranigmark/curso-analisis-exploratorio-datos-platzi/main/Traffic_Crashes1.csv' token_map_plot='pk.eyJ1IjoiY2hlbWlza3kiLCJhIjoiY2tnOGNhcXk3MGZ3eDJ5b2FxZ3ViajN1MyJ9.t3R24lWTwzTQwyJw4vuWFw'

import pandas as pd

Chicago_df=pd.read_csv(Chicago_data)

Chicago_df['CRASH_DATE'] = Chicago_df['CRASH_DATE'].apply(lambda x: pd.to_datetime(x, errors='coerce', utc=True))

import plotly.express as px px.set_mapbox_access_token(token_map_plot)

df = px.data.carshare() fig = px.scatter_mapbox(Chicago_df, lat="LATITUDE", lon="LONGITUDE", color="CRASH_HOUR", size="NUM_UNITS", color_continuous_scale=px.colors.cyclical.IceFire, size_max=15, zoom=10) fig.show()

Chicago_df['Lat_round']= round(Chicago_df['LATITUDE'],2) Chicago_df['Long_round']= round(Chicago_df['LONGITUDE'],2)

df = px.data.carshare() fig = px.scatter_mapbox(Chicago_df, lat="Lat_round", lon="Long_round", color="CRASH_HOUR", size="NUM_UNITS", color_continuous_scale=px.colors.cyclical.IceFire, size_max=15, zoom=10) fig.show()

Chicago_df['NUM_UNITS'].plot()

import scipy.stats as ss

ss.variation(Chicago_df['NUM_UNITS'])

import matplotlib.pyplot as plt

plt.hist(Chicago_df[['NUM_UNITS']])

tab=pd.crosstab(index=Chicago_df['CRASH_MONTH'],columns='Frecuencia')

plt.bar(tab.index,tab['Frecuencia'])

#Llamamos el set de datos público import pandas as pd import altair as alt Chicago_data = 'https://raw.githubusercontent.com/terranigmark/curso-analisis-exploratorio-datos-platzi/main/Traffic_Crashes1.csv' Chicago_df=pd.read_csv(Chicago_data) #Transformaciones básicas Chicago_df['CRASH_DATE'] = Chicago_df['CRASH_DATE'].apply(lambda x: pd.to_datetime(x,errors='coerce', utc=True))

Chicago_df.head()

Chicago_df.info()

report_1=Chicago_df.groupby(['LIGHTING_CONDITION','REPORT_TYPE','CRASH_HOUR']).agg({'NUM_UNITS':'sum'}) report_1=report_1.reset_index() report_1

alt.Chart(report_1).mark_bar().encode( x='LIGHTING_CONDITION', y='NUM_UNITS', color='REPORT_TYPE' ).properties(width=220)

report_2=Chicago_df.groupby(['LIGHTING_CONDITION','REPORT_TYPE','CRASH_HOUR']).agg({'NUM_UNITS':['sum','min','max']}) report_2=report_1.reset_index() report_2

#Llamamos el set de datos público import pandas as pd url_wine_red = 'https://raw.githubusercontent.com/terranigmark/curso-analisis-exploratorio-datos-platzi/main/winequality-red.csv' url_wine_white = 'https://raw.githubusercontent.com/terranigmark/curso-analisis-exploratorio-datos-platzi/main/winequality-white.csv'

red=pd.read_csv(url_wine_red,delimiter=';') white=pd.read_csv(url_wine_white,delimiter=';')

red.head()

white.head()

red['color']='red' white['color']='white'

red.append(white)

pd.concat([white,red])

left=pd.DataFrame({'Key':['key1','key2','key3'], 'A':['a1','a2','a3'] }) left

right=pd.DataFrame({'Key':['key3','key4','key3'], 'A':['a1','a2','a3'] }) right