Análisis de los 25 retailers más grandes de Estados Unidos

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

df = pd.read_csv('/work/largest_us_retailers.csv') df_sales = df.sort_values('Sales', ascending=0) df_sales.head()

#Promedio sin la compañía dominante avg = df_sales['Sales'][1:].mean() print(avg)

#Promedio con la compañia dominante df['Sales'].mean()

x = ['Con Dominante', 'Sin Dominante'] y = [71063, 46602] plt.bar(x, y) plt.show()

x = ['Más Alto', 'Promedio', 'Más Bajo'] y = [115000, 46602, 16572] plt.bar(x, y) plt.style.use('ggplot')

x = df_sales['Sales'][1:] plt.hist(x) plt.style.use('ggplot')

df_stores = df.sort_values('Stores', ascending=True) x = df_stores['Stores'] plt.hist(x) plt.style.use('ggplot')

bins = [i for i in range(0, 2001, 100)] plt.hist(x, bins) plt.style.use('ggplot')

bins = [i for i in range(2000, 4001, 100)] plt.hist(x, bins) plt.style.use('ggplot')

plt.scatter(df_sales['Stores'], df_sales['Sales']) plt.title('Sales & Stores') plt.xlabel('Stores') plt.ylabel('Sales') plt.show()

max_sales = df_sales['Sales'][1:].max() min_sales = df_sales['Sales'].min() print(max_sales) print(min_sales) x = ['Max', 'Min'] y = [max_sales, min_sales] plt.bar(x, y)

#Top 5 empresas que más tiendas físicas tienen df_stores = df.sort_values('Stores', ascending=False) x = df_stores['Company'][:5] y = df_stores['Stores'][:5] print(df_stores['Company'][:5]) plt.bar(x, y) plt.xticks(rotation=45) plt.show()

#Top 5 empresas que más ventas tienen x = df_sales['Company'][:5] y = df_sales['Sales'][:5] print(df_sales['Company'][:5]) plt.bar(x,y) plt.xticks(rotation=10) plt.show()

category = df.groupby('Category')['Sales'].sum() print(category.sort_values(ascending=False))

x = ['Supercenters', 'Grocery', 'Drug Stores', 'Home Improvment', 'Warehouse Club', 'Electronic/Mail Order', 'Warehouse Clubs', 'Department Stores', 'Dollar Stores', 'Electronics', 'Apparel'] y = category.sort_values(ascending=False) plt.bar(x, y) plt.xticks(rotation=90) plt.show()

df_sales_avg = df.sort_values('Sales/Avg. Store', ascending=False) df_sales_avg.head()

x = df_sales_avg['Company'][:15] y = df_sales_avg['Sales/Avg. Store'][:15] plt.bar(x, y) plt.xticks(rotation = 90) plt.show()

df[df.Category == 'Electronic/Mail Order']

df.sort_values('Company', ascending=True)

df_company = df.sort_values('Company', ascending=True) df_company = df_company.drop(6) df_company = df_company.drop(11) df_company = df_company.drop(0) df_company['Sales'].mean() # Promedio de ventas de compañias con solo tiendas físicas

x = ['Amazon', 'Apple incl. Online', 'Average'] y = [71687, 37664, 45868] plt.bar(x, y) plt.ylabel('Sales') plt.show()

y = df.groupby('Category')['Stores'].sum() x = df['Category'].drop_duplicates() x = x.sort_values(ascending=True)[:11] print(y.sort_values(ascending=False)) plt.bar(x, y) plt.xticks(rotation=90) plt.show()

stores_per_category = df.groupby('Category')['Stores'].sum() bins = [i for i in range(0,25,10)] print(stores_per_category.sort_values(ascending=True)) plt.hist(stores_per_category) plt.xlabel('Stores') plt.show()

x = df.groupby('Category')['Sales/Avg. Store'].mean() list = df['Category'].drop_duplicates().sort_values(ascending=True) list = list[:11] print(x.sort_values(ascending=True)) plt.bar(list, x) plt.xticks(rotation=90) plt.show()