# A veces necesitamos instalar nuevas librerías en nuestros proyectos
!pip install openpyxl==3.0.10
# imports
import numpy as np
import pandas as pd
import sqlite3 as sql3
import openpyxl
import matplotlib.pyplot as plt
import seaborn as sns
# Levanto los datos en 3 diferentes dataframes
# Articulos
conn = sql3.connect('/work/data/articles.db')
sql_query = pd.read_sql_query('SELECT * FROM articles', conn)
df_articles = pd.DataFrame(sql_query, columns=['article_id', 'article_name', 'unit_price'])
# Vendedores
df_sellers = pd.read_excel('/work/data/sellers.xlsx', index_col=0)
# Ordenes
df_orders = pd.read_csv('/work/data/orders.csv')
# Exploración del df de artículos
print('Muestra de datos')
print(df_articles.head()) # head() 5 Filas por defecto
print('\nFormato del dataframe')
print(df_articles.shape)
print('\nBúsqueda de valores null por columna')
print(df_articles.isnull().sum())
print('\nFormato de los datos por columna')
print(df_articles.dtypes)
# Exploración del df de vendedores
print('Muestra de datos')
print(df_sellers) # head() 5 Filas por defecto
print('\nFormato del dataframe')
print(df_sellers.shape)
print('\nBúsqueda de valores null por columna')
print(df_sellers.isnull().sum())
print('\nFormato de los datos por columna')
print(df_sellers.dtypes)
# Exploración del df de órdenes
print('Muestra de datos')
print(df_orders.head()) # head() 5 Filas por defecto
print('\nFormato del dataframe')
print(df_orders.shape)
print('\nBúsqueda de valores null por columna')
print(df_orders.isnull().sum())
print('\nFormato de los datos por columna')
print(df_orders.dtypes)
df_articles['unit_price'] = df_articles['unit_price'].astype(float)
print(df_articles.dtypes)
# https://pandas.pydata.org/docs/user_guide/indexing.html
# https://towardsdatascience.com/how-to-use-loc-and-iloc-for-selecting-data-in-pandas-bd09cb4c3d79
# https://stackoverflow.com/questions/28754603/indexing-pandas-data-frames-integer-rows-named-columns
my_df = df_orders.copy() # shallow copy
# Cambio el indice del df de artículos
df_articles.set_index('article_id', inplace=True)
my_df = my_df.assign(article_name = my_df['article_id'])
my_df = my_df.assign(total_amount = my_df['article_id'])
my_df = my_df.assign(seller_name = my_df['seller_id'])
# print(df_articles)
# print()
# my_df
for i in range(max(my_df.count())):
# print(i)
# SINTAXIS: df_articles.loc[indice][columna]
# [indice]: va a ser el dato que obtengo de [my_df.loc[i, 'article_id']]
# o sea, tomo registro a registro el article_id y lo uso para extraer el nombre del artículo (article_name) de df_articles (tabla)
# print(df_articles.loc[my_df.loc[i ,'article_id']]['article_name'])
article = df_articles.loc[my_df.loc[i ,'article_id']]['article_name']
# print(article)
# Asignar a cada valor id de la columna 'article_name' de my_df, el nombre del artículo
my_df.loc[i, 'article_name'] = article
#my_df
# hacemos lo mismo con total_amount
my_df.loc[i, 'total_amount'] = my_df.loc[i, 'quantity']*df_articles.loc[my_df.loc[i ,'article_id']]['unit_price']
#my_df
# Columna de seller name
my_df.loc[i, 'seller_name'] = df_sellers.loc[my_df.loc[i ,'seller_id']]['seller_name']
# elimino las columnas que no necesito de my_df
my_df.drop(['order_id', 'article_id', 'seller_id'], axis='columns', inplace=True)
print(my_df)
# my_df.loc[:, 'quantity']
# my_df.loc[:, ['quantity','country_name']]
# my_df.loc[0:5, ['quantity','country_name']]
my_df.iloc[:, 1]
# my_df.iloc[:, [1,2]]
# my_df.iloc[0:6, [1,2]]
my_df.iloc[0:5, [1,2]]
# RESOLUCIÓN ANALÍTICA
# Si no filtro por 'quantity' toma las series numéricas
# df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False)
# print(df7.head())
# print(df7[['quantity']].head())
# print()
# Tomamos article_name como una columna más
# df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False).reset_index()
# print(df7.head())
# df7_2 = df7[['article_name', 'quantity']].groupby('article_name').sum('quantity').sort_values('quantity', ascending=False)
# print(df7_2.head())
# print()
# print(df7_2.head().index)
# print(df7_2.index[0]) # toma correctamente el index
# Vista tipo Serie
# df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False).head()
# df7 = my_df.groupby(by='article_name')[['quantity'] + ['total_amount']].sum().sort_values('quantity',ascending=False).head()
# print(df7)
# print(df7.head().index)
# Vista tipo Serie
# df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False)
# print(df7.iloc[0:5])
# Vista tipo Serie (reset index)
# df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False).reset_index()
# print(df7.iloc[0:5])
# Vista tipo Serie
# df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False)
# df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False)
# print(df7.loc['HDD':'Netbook'])
# print(df7.loc['HDD':'Netbook']['quantity'])
# print(df7.head())
# df7 = my_df.groupby(by='article_name').agg({'quantity':'sum'}).sort_values('quantity',ascending=False)
# print(df7.head())
# df7 = my_df.groupby(by='article_name').agg({'quantity':'sum'}).rename(columns={'quantity':'Cantidad'}).sort_values('Cantidad',ascending=False)
# print(df7.head())
# df7 = my_df.groupby(by='article_name').agg({'quantity':'sum'}).reset_index().rename(columns={'quantity':'Cantidad'}).sort_values('Cantidad',ascending=False)
# print(df7.head())
df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False).head()
pd.options.display.float_format= '$ {:,.2f}'.format
# print(df7[['quantity']].head())
# print(df7[['quantity', 'total_amount']].head(5))
print(df7[['quantity', 'total_amount']])
# RESOLUCIÓN GRÁFICA
sns.barplot(data=df7, x=df7.index, y='quantity')
def add_value_label(x_list, y_list):
for i in range(0, len(x_list)):
plt.annotate(y_list[i], (i, y_list[i]/2), ha="center")
add_value_label(df7.index, df7["quantity"])
plt.xticks(rotation=45)
plt.show()
# RESOLUCIÓN ANALÍTICA
df2 = my_df.groupby(by='article_name').sum().sort_values('total_amount', ascending=False).head(5)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df2['total_amount'])
# 'article_name' es el index
# print()
# print(df2.index[0])
# print()
# print(df2.reset_index().iloc[0])
# print()
# for i in range(5):
# # print(df2.index[i])
# print(df2.reset_index().iloc[i])
# print()
# print()
# print(df2.reset_index())
# RESOLUCIÓN GRÁFICA
import math
sns.barplot(data=df2, x=df2.index, y='total_amount')
def add_value_label(x_list, y_list):
for i in range(0, len(x_list)):
plt.annotate(math.ceil(y_list[i]), (i, y_list[i]/2), ha="center")
add_value_label(df2.index, df2["total_amount"])
plt.xticks(rotation=45)
plt.show()
print()
plt.pie(x=df2['total_amount'], labels=df2.index, autopct='%1.2f%%')
plt.show()
# RESOLUCIÓN ANALÍTICA
df4 = my_df.groupby(by='seller_name').sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df4[['quantity'] + ['total_amount']].head(5))
# RESOLUCIÓN GRÁFICA
plt.bar(df4.index, df4['total_amount'])
plt.xticks(rotation=90)
plt.show()
# RESOLUCIÓN ANALÍTICA
df5 = my_df.groupby(by='week').sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df5[['quantity'] + ['total_amount']])
# RESOLUCIÓN GRÁFICA
plt.bar(df5.index, df5['total_amount'])
plt.show()
# RESOLUCIÓN
df_mexico = my_df[my_df['country_name'] == 'Mexico']
df_peru = my_df[my_df['country_name'] == 'Peru']
df = df_mexico.groupby(by='week').sum()
df2 = df_peru.groupby(by='week').sum()
print("Ventas en unidades Mexico")
print(df[['quantity']])
print()
print("Ventas en unidades Peru")
print(df2[['quantity']])
weeks = [1,2,3,4]
fig, ax = plt.subplots()
ax.plot(weeks, df['quantity'], label='Mexico')
ax.plot(weeks, df2['quantity'], label='Peru')
ax.legend(loc = 'upper right')
plt.show()
# RESOLUCIÓN
df = my_df.groupby(by='country_name').sum().sort_values('total_amount', ascending=False).head()
pd.options.display.float_format= '$ {:,.2f}'.format
print(df[['total_amount']])
print()
plt.pie(x=df['total_amount'], labels=df.index, autopct='%1.2f%%')
plt.show()
# RESOLUCIÓN
import math
df2 = my_df.groupby(['seller_name', 'article_name']).sum().sort_values('total_amount', ascending=False).head()
df1 = my_df.groupby(['seller_name']).sum().sort_values('total_amount', ascending=False).head()
pd.options.display.float_format= '$ {:,.2f}'.format
print(df2.loc[(df2['total_amount']>=100000) ,['total_amount']])
def add_value_label(x_list, y_list):
for i in range(0, len(x_list)):
plt.annotate(math.ceil(y_list[i]), (i, y_list[i]/2), ha="center")
add_value_label(df2.index, df2["total_amount"])
plt.bar(df1.index, df2['total_amount'])
plt.xticks(rotation=90)
plt.show()
df6 = my_df[my_df['country_name'] == 'Brazil']
#A partir del anterior, ordenar vendedores por total de ventas
vendedores_pais = df6.groupby('seller_name').sum().sort_values('total_amount', ascending=False)
vendedores_pais.head()
plt.bar(vendedores_pais.index,vendedores_pais['total_amount'],
color = ['green' if x in vendedores_pais.index[0:5] else 'blue' for x in vendedores_pais.index]) #Color verde para los mejores 5
plt.xticks(rotation = 90)
plt.title("Desempeño vendedores del país que más compra")
plt.xlabel("Vendedores")
plt.ylabel("Total de Ventas")
plt.show()
df_brazil = my_df[my_df['country_name'] == 'Brazil']
print(df_brazil[['seller_name','total_amount', 'quantity']].groupby('seller_name').sum().sort_values('total_amount', ascending=False))
print()
df_brazil_bars = df_brazil[['seller_name','total_amount']].groupby('seller_name').sum('total_amount').sort_values('total_amount', ascending=False)
print(df_brazil_bars)
print()
df_brazil_line = df_brazil[['seller_name','quantity']].groupby('seller_name').sum('quantity').sort_values('quantity', ascending=False).reset_index()
print(df_brazil_line)
fig, ax1 = plt.subplots()
# ax1: axes1
# sns.barplot(data = df_brazil_bars, x='seller_name', y='total_amount', ax=ax1, color='C3')
sns.barplot(data=df_brazil_bars, x = df_brazil_bars.index, y='total_amount', ax=ax1, color='C3')
# ax: axes
plt.xticks(rotation=90)
ax2 = ax1.twinx()
# ax2: axes2 = ax1.twinx()
sns.lineplot(data = df_brazil_line, x='seller_name', y='quantity', ax=ax2, color='C11')
plt.xticks(rotation=90)
plt.title('Top sellers in Brazil')
ax1.set_xlabel("Seller Name")
ax1.set_ylabel("Income ($)")
ax2.set_ylabel("Quantity (line)")
plt.show()