# 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 # levantar excel
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('\nBusqueda de valores nulls 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()) # head() 5 Filas por defecto
print('\nFormato del dataframe')
print(df_sellers.shape)
print('\nBusqueda de valores nulls 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('\nBusqueda de valores nulls 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 índice 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
# 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' (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']
# 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 del df
my_df.drop(['order_id', 'article_id', 'seller_id'], axis='columns', inplace=True)
print(my_df)
# my_df.loc[:, 'quantity']
# my_df.loc[0, ['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]]
# 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)
# 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())
# print(df7[['quantity', 'total_amount']])
# RESOLUCIÓN GRÁFICA
# Opción 1 - Count
# sns.countplot(my_df, x='article_name')
# Opción 2 - barplot
sns.barplot(data=df7, x=df7.index, y='quantity')
# Opción 3 - barplot
# xs = ["HDD", "Tablet", "SDD", "Mouse", "Netbook"]
# ys = [413, 374, 372, 322, 320]
# sns.barplot(x=xs, y=ys)
plt.xticks(rotation=90) # 'vertical'
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)
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
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']])
# 'week' es el index
# RESOLUCIÓN GRÁFICA
plt.bar(df5.index, df5['total_amount'])
plt.show()