import pandas as pd

df_survey = pd.read_csv('kaggle_survey_2020_responses.csv', dtype={'Time from Start to Finish (seconds)': object}) #Se declara el dipo de dato de la columa (0) para evitar el error

#Configuración de la impresión de columnas y filas al máximo para ver la estructura completa del dataframe pd.set_option("display.max_columns", None) pd.set_option("display.max_rows", None) df_survey.head(3)

df_survey.shape

df_survey.dtypes[0:10]

df_survey.describe().T[0:5]

df_survey0 = pd.read_csv('kaggle_survey_2020_responses.csv', usecols=['Q1','Q2','Q3']) df_survey0.head(5)

questions = df_survey.iloc[:1,:].T data = df_survey.iloc[1:,:]

questions.head(5)

data['Q1'].value_counts(normalize=True).mul(100).round(2).sort_index()

data['Q1'].value_counts(normalize=True).mul(100).round(2).sort_index().plot.bar(color="mediumturquoise")

pd.set_option("display.max_rows", None) data[['Q3','Q4']].groupby(['Q3','Q4']).agg(count=('Q4', 'count')).sort_values(['Q3','count'], ascending=[True,False])

questions2 = questions.loc[['Q3', 'Q4', 'Q5', 'Q7_Part_1', 'Q24']] data2 = data[['Q3','Q4','Q5','Q7_Part_1','Q24']]

#Se retira el limite al ancho de columna para obtener las preguntas completas. pd.set_option('display.max_colwidth', None) questions2

data2.head()

#Reemplazar una respuesta extensa por una recortada pd.options.mode.chained_assignment = None data2['Q4'] = data2['Q4'].replace(["Some college/university study without earning a bachelor’s degree"] , "University study without degree") q4 = data2['Q4'].value_counts(normalize=True, dropna=False).mul(100).reset_index() q4.plot.bar(x='index', y='Q4' , xlabel = 'Level of formal education' , title='Highest level of formal education (or plan to attain within the next 2 years)' , color="lightpink" , legend=False)