# imports
import numpy as np
import pandas as pd
import sqlite3 as sql3
import matplotlib.pyplot as plt
import seaborn as sns
# Levanto los datos en 3 diferentes dataframes
# ARTÍCULOS
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'])
print(df_articles)
# VENDEDORES
df_sellers = pd.read_excel('/work/data/sellers.xlsx', index_col=0)
print(df_sellers)
# ÓRDENES
df_orders = pd.read_csv('/work/data/orders.csv')
print(df_orders)
# Exploración del df de artículos
print('Muestra de datos')
print(df_articles.head())
print('\nFormato del dataframe')
print(df_articles.shape)
print('\nBúsqueda de valores nulos')
print(df_articles.isnull().sum())
print('\nFormato de los datos')
print(df_articles.dtypes)
# Exploración del df de vendedores
print('Muestra de datos')
print(df_sellers.head())
print('\nFormato del dataframe')
print(df_sellers.shape)
print('\nBúsqueda de valores nulos')
print(df_sellers.isnull().sum())
print('\nFormato de los datos')
print(df_sellers.dtypes)
# Exploración del df de órdenes
print('Muestra de datos')
print(df_orders.head())
print('\nFormato del dataframe')
print(df_orders.shape)
print('\nBúsqueda de valores nulos')
print(df_orders.isnull().sum())
print('\nFormato de los datos')
print(df_orders.dtypes)
df_articles['unit_price'] = df_articles['unit_price'].astype(float)
print(df_articles.dtypes)
# Creo una copia del df_orders
my_df = df_orders.copy()
# Cambio el índice del df_articles
df_articles.set_index('article_id', inplace=True)
print(df_articles.head())
print(my_df.head())
# agrego las columnas que me faltan
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(my_df.head())
# reemplazar los datos ne las nuevas columnas
for i in range(len(my_df.index)):
# columna article_name
# cargo el nombre del artículo en una variable
article = df_articles.loc[my_df.loc[i]['article_name']]['article_name']
# se lo asigno a la columna y registro que corresponde
my_df.loc[i,'article_name']= article
# columna 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_name']]['seller_name']
#Agregado para el trabajo
my_df['week'] = my_df['week'].astype(str)
print(my_df.head())
# elimino las columnas que no necesito
my_df.drop(['order_id', 'article_id','seller_id'], axis='columns', inplace=True)
print(my_df.head())
d1=pd.DataFrame({'mes': ['ene','feb','mar','abr'], 'ventas':[10,20,30,15]})
d2=pd.DataFrame({'mes': ['ene','feb','mar','abr'], 'costos':[7,16,25,12]})
print(pd.merge(d1,d2))
# RESOLUCIÓN GRÁFICA
e=[0.1,0,0,0,0]
plt.pie(x=my_df3['total_amount'],explode=e, labels=my_df3.index,autopct='%1.2f%%')
plt.show()
# RESOLUCIÓN ANALÍTICA
df5=(my_df.groupby('week').sum()).sort_values('total_amount',ascending=False)
print(df5)
# RESOLUCIÓN GRÁFICA
plt.bar(df5.index,df5['total_amount'])
plt.xlabel('Semana')
plt.ylabel('Total ventas')
plt.show()
art2 = my_df[(my_df['article_name']== 'Full Pc') & ((my_df['country_name'] == 'Argentina') | (my_df['country_name']=='Brazil'))]
my_df60=(my_df.groupby('country_name').sum()).sort_values('total_amount',ascending=False)
#print(my_df60)
dfc=my_df[((my_df['country_name']=='Argentina') | (my_df['country_name']=='Brazil')| (my_df['country_name']=='Colombia')) & ((my_df['article_name']=='Full Pc'))]
dfc = dfc.groupby(["week","country_name"]).sum().sort_values('total_amount',ascending=False)
dfc.reset_index('country_name', inplace=True)
#print(dfc)
sns.barplot(dfc.index.get_level_values(0), 'total_amount', data =dfc, hue='country_name')
plt.ylabel('Monto de ventas Full Pc')
plt.xlabel('Semana')
plt.show()