Análisis de los 25 retailers más grandes de Estados Unidos

# Importamos las librerías necesarias import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns

# Importamos los datos con Pandas retail = pd.read_csv("largest_us_retailers.csv")

retail.head(10)

retail.shape

retail.dtypes

retail[["Sales","Company"]].max()

retail_without_wallmart = retail[retail["Company"] != "Walmart US"].sort_values("Sales", ascending=0)

retail.sort_values("Sales", ascending=0)

x = retail['Company'][:5] y = retail['Sales'][:5] plt.bar(x, y) plt.title('Top 5 retailers') plt.xlabel('Company') plt.ylabel('Sales') plt.xticks(rotation='vertical') plt.show()

round(retail_without_wallmart["Sales"].mean(),2)

sns.histplot(retail, x="Sales")

print(f"La compañía con menos tiendas tiene {retail['Stores'].min()}") sns.histplot(retail,x="Stores")

retail[["Stores","Sales"]].corr()

sns.scatterplot(data=retail, x="Stores", y="Sales")

minimo_ventas = retail["Sales"].min() maximo_ventas = retail["Sales"].max() print(f"El rango de las ventas está entre {minimo_ventas} y {maximo_ventas}")

top5_tiendas = retail[["Company","Stores"]][:5].sort_values("Stores",ascending=False) top5_tiendas

top_mayor_ventas = retail.sort_values("Sales", ascending=False) top5_mayor_ventas = top_mayor_ventas[:5] stores = top5_tiendas["Company"].values sales = top5_mayor_ventas["Company"].values companies = [] for index,company in enumerate(stores): if company in sales: companies.append(company) companies

retail["Category"].isnull().count()

retail["Category"].unique

clean_detail = retail.drop(retail[retail['Category'].isnull()].index)

x = clean_detail['Category'] y = clean_detail['Sales'] plt.bar(x, y) plt.title('Category on more sales') plt.xlabel('Category') plt.ylabel('Sales') plt.xticks(rotation='vertical') plt.show()

sns.scatterplot(data=clean_detail,x="Stores", y="Sales", hue="Company")

sns.boxplot(data=clean_detail, x="Stores",y="Sales",orient="vertical")

online = retail[retail["Stores"].isnull()] online["Company"]

x = online['Company'] y = online['Sales'] plt.bar(x, y) plt.title('Online retailers') plt.xlabel('Company') plt.ylabel('Sales') plt.xticks(rotation='vertical') plt.show()