import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt

df = pd.read_csv('/work/largest_us_retailers.csv') df.head()

df_sorted = df.sort_values('Sales', ascending= 0) df_sorted

df_size = df_sorted.size df_shape = df_sorted.shape df_info = df_sorted.info print('La cantidad de valores totales en el Data Frame es de', str(df_size), 'datos') print('La cantidad de Filas y Columnas respectivamente es de', df_shape) print(' ') print('Por último vamos a verificar la integridar de la información y de esta manera determinar si hace falta informacion en en Data Frame') df_info()

#Tip: slicing df_drop = df_sorted.drop(0).sort_values('Sales', ascending = 0) #Choose n companies to see their sales #compañia = int(input('Cuantas compañias quieres ver')) #com = int(compañia) #Slicing data using .head(##) y = df_drop['Sales'].head(24) x = df_drop['Company'].head(24) #Customization #Figure size fig,ax = plt.subplots(figsize = (16,10)) # Plot Title plt.title('Ventas', loc = 'Left',fontsize = 20, color = 'black') plt.xlabel('Company') plt.ylabel('Sales') plt.xticks(rotation='vertical') g = 'green' #Add x, y gridlines ax.grid(b =True, color = 'grey', linestyle = '-', linewidth = 0.5, alpha= 0.4) #Add text watermark fig.text(0.88, 0.85, "Data Academy Challenge, Y. Torres", fontsize = 15, color = 'black', ha = 'right', va = 'bottom', alpha = 0.9) #Show Plot plt.bar(x,y, color = g, width = 0.8) #Mean of sales of companies selected msales = df_drop['Sales'].head(compañia).mean() #msales = dsales.mean() print('El promedio total de ventas de las compañias es $', msales )

#Choose n companies to see their sales print('Hey buen dia, solo te comento que esta vizualización contempla la compañia dominante') #compañia = int(input('Cuantas compañias quieres ver')) #Slicing data using .head(##) y = df['Sales'].head(25) x = df['Company'].head(25) #Customization #Figure size fig,ax = plt.subplots(figsize = (16,10)) # Plot Title plt.title('Ventas Totales', loc = 'Left',fontsize = 20, color = 'black') plt.xlabel('Company') plt.ylabel('Sales') plt.xticks(rotation='vertical') g = 'gray' #Add x, y gridlines ax.grid(b =True, color = 'grey', linestyle = '-', linewidth = 0.5, alpha= 0.4) #Add text watermark fig.text(0.85, 0.85, "Data Academy Challenge, Y. Torres", fontsize = 15, color = 'black', ha = 'right', va = 'bottom', alpha = 0.9) #Show Plot plt.bar(x,y, color = g, width = 0.8) #sum of sales of companies selected sales = df_drop['Sales'].head(compañia).sum() print('La suma total de ventas de las compañias es $', sales.round(2) )

#Choose n companies to see their sales #company = input('Cuantas compañias quieres ver') #comp = int(company) y = df['Stores'] x = df['Company'] #Figure Size fig,ax = plt.subplots(figsize = (10,9)) #Labels plt.title('Presencia de compañias',fontsize = 20,loc = 'left', color ='black') plt.xlabel('Compañias') plt.ylabel('Cantidad de tiendas') plt.text(20, .025, 'Data Academy Y.Torres') plt.xticks(rotation='vertical') plt.grid(True, linestyle = '--', linewidth = 0.5, alpha = 0.4) plt.bar(companies,store, color = 'green')

#Comparativa tomando en cuenta la compañia dominante y la compañia no dominante comparativa = int(input('Seleccione el tipo de comaprativa que quiere hacer, 1 para incluir la compañia dominante y 2 para no incluir la compañia')) if comparativa == 2: plt.grid(visible= True, linestyle = '--', color = 'grey', linewidth = 0.4, alpha = 0.4) plt.title('correlation of stores vs saless') plt.xlabel('stores') plt.ylabel('sales') a = df_drop['Stores'] b = df_drop['Sales'] plt.scatter(a,b) elif: plt.title('correlation of stores vs saless') plt.xlabel('stores') plt.ylabel('sales') plt.grid(visible= True, linestyle = '--', color = 'grey', linewidth = 0.4, alpha = 0.4) x= df['Stores'] y= df['Sales'] plt.scatter(x,y) else: print('Elige bien, solo hay dos opciones')

#Tip Max - Min range_drop = max(df_drop['Sales']) - min(df_drop['Sales']) range_full = max(df['Sales']) - min(df['Sales']) print('El rango es de $',range_full,'DLS') print('El rango es de $',range_drop,'DLS')

# Pista pregunta de ejemplo df_phsto = df.sort_values('Stores', ascending = 0) b = df['Stores'].head(5) a = df['Company'].head(5) #Figure Size fig,ax = plt.subplots(figsize = (10,8)) #cutomizing plt.title('Top 5 empresas que mas tiendas físicas tienen', fontsize = 15, loc = 'left') plt.xlabel('Compañias', fontsize = 14, color = 'gray') plt.ylabel('Tiendas', fontsize = 14, color = 'gray') plt.grid(visible= True, linestyle = '--', color = 'grey', linewidth = 0.4, alpha = 0.4) #plot plt.bar(a,b, color = 'green', width = 0.5 )

#Figsize fig,ax = plt.subplots(figsize = (10,8)) #cutomizing plt.title('Componies with higher sales', fontsize = 15, loc = 'left') plt.xlabel('Companies', fontsize = 14, color = 'gray') plt.ylabel('Sales', fontsize = 14, color = 'gray') plt.grid(visible= True, linestyle = '--', color = 'grey', linewidth = 0.4, alpha = 0.4) plt.bar(df['Company'].head(5),df['Sales'].head(5))