# A veces necesitamos instalar nuevas librerías en nuestros proyectos
!pip install openpyxl==3.0.10
Collecting openpyxl==3.0.10
Downloading openpyxl-3.0.10-py2.py3-none-any.whl (242 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 242.1/242.1 KB 19.2 MB/s eta 0:00:00
Collecting et-xmlfile
Downloading et_xmlfile-1.1.0-py3-none-any.whl (4.7 kB)
Installing collected packages: et-xmlfile, openpyxl
Successfully installed et-xmlfile-1.1.0 openpyxl-3.0.10
WARNING: You are using pip version 22.0.4; however, version 22.1.2 is available.
You should consider upgrading via the '/root/venv/bin/python -m pip install --upgrade pip' command.
# 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')
query1 = pd.read_sql_query('SELECT * FROM articles', conn)
df_articles = pd.DataFrame(query1, 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)
order_id week article_id quantity seller_id country_name
0 15024 1 20039 10 10 Peru
1 15025 1 20029 15 5 Peru
2 15026 1 20024 5 14 Bolivia
3 15027 1 20018 9 14 Brazil
4 15028 1 20035 6 15 Mexico
.. ... ... ... ... ... ...
995 16019 4 20021 1 7 Brazil
996 16020 4 20040 15 15 Brazil
997 16021 4 20040 2 11 Colombia
998 16022 4 20018 14 11 Brazil
999 16023 4 20026 12 9 Brazil
[1000 rows x 6 columns]
# 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 por columna')
print(df_articles.isnull().sum())
print('\nFormato de los datos')
print(df_articles.dtypes)
Muestra de datos
article_id article_name unit_price
0 20015 Smartphone 525.00
1 20016 Full Pc 2127.81
2 20017 Monitor 230.00
3 20018 Tablet 130.00
4 20019 Desk 130.10
Formato del dataframe
(31, 3)
Búsqueda de valores nulos por columna
article_id 0
article_name 0
unit_price 0
dtype: int64
Formato de los datos
article_id int64
article_name object
unit_price object
dtype: object
# 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 por columna')
print(df_sellers.isnull().sum())
print('\nFormato de los datos')
print(df_sellers.dtypes)
Muestra de datos
seller_name
seller_id
1 Aveline Swanwick
2 Jase Doy
3 Oliviero Charkham
4 Cornie Wynrehame
5 Ewell Peres
Formato del dataframe
(15, 1)
Búsqueda de valores nulos por columna
seller_name 0
dtype: int64
Formato de los datos
seller_name object
dtype: object
# 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 por columna')
print(df_orders.isnull().sum())
print('\nFormato de los datos')
print(df_orders.dtypes)
Muestra de datos
order_id week article_id quantity seller_id country_name
0 15024 1 20039 10 10 Peru
1 15025 1 20029 15 5 Peru
2 15026 1 20024 5 14 Bolivia
3 15027 1 20018 9 14 Brazil
4 15028 1 20035 6 15 Mexico
Formato del dataframe
(1000, 6)
Búsqueda de valores nulos por columna
order_id 0
week 0
article_id 0
quantity 0
seller_id 0
country_name 0
dtype: int64
Formato de los datos
order_id int64
week int64
article_id int64
quantity int64
seller_id int64
country_name object
dtype: object
df_articles['unit_price'] = df_articles['unit_price'].astype(float)
print(df_articles.dtypes)
article_id int64
article_name object
unit_price float64
dtype: object
# Creo una copia del df base
my_df = df_orders.copy()
# Cambio el índice del df artículos
df_articles.set_index('article_id', inplace=True)
print(my_df)
#print(df_articles)
order_id week article_id quantity seller_id country_name
0 15024 1 20039 10 10 Peru
1 15025 1 20029 15 5 Peru
2 15026 1 20024 5 14 Bolivia
3 15027 1 20018 9 14 Brazil
4 15028 1 20035 6 15 Mexico
.. ... ... ... ... ... ...
995 16019 4 20021 1 7 Brazil
996 16020 4 20040 15 15 Brazil
997 16021 4 20040 2 11 Colombia
998 16022 4 20018 14 11 Brazil
999 16023 4 20026 12 9 Brazil
[1000 rows x 6 columns]
# Agrego algunas columnas y pongo el campo que me va a servir de "ancla"
my_df = my_df.assign(article_name = my_df['article_id'])
my_df = my_df.assign(total_amount = my_df['article_id']) # voy a necesitar el unit_price
my_df = my_df.assign(seller_name = my_df['seller_id'])
# reeplazar los valores en el nuevo df
# df_articles[?]['article_name']
for i in range(len(my_df.index)):
# len... devuelve la cantidad de registros
article = df_articles.loc[my_df.loc[i]['article_name']]['article_name']
# reemplazo en la columna 'article_name'
my_df.loc[i,'article_name'] = article
# modificar la columna total_amount
my_df.loc[i,'total_amount'] = my_df.loc[i,'quantity'] * df_articles.loc[my_df.loc[i]['total_amount']]['unit_price']
# modifical la columna 'seller_name'
my_df.loc[i,'seller_name'] = df_sellers.loc[my_df.loc[i]['seller_name']]['seller_name']
# elimino las columnas que no necesito
my_df.drop(['order_id','article_id','seller_id'], axis='columns', inplace=True)
print(my_df)
week quantity country_name article_name total_amount seller_name
0 1 10 Peru Water Cooling 675.0 Cirilo Grandham
1 1 15 Peru Mouse 454.5 Ewell Peres
2 1 5 Bolivia Netbook 725.0 Janel O'Curran
3 1 9 Brazil Tablet 1170.0 Janel O'Curran
4 1 6 Mexico Case 227.4 Daisie Slograve
.. ... ... ... ... ... ...
995 4 1 Brazil Modem 67.5 Kati Innot
996 4 15 Brazil Heatsink 150.0 Daisie Slograve
997 4 2 Colombia Heatsink 20.0 Vasily Danilyuk
998 4 14 Brazil Tablet 1820.0 Vasily Danilyuk
999 4 12 Brazil SDD 264.0 Onida Cosely
[1000 rows x 6 columns]
# RESOLUCIÓN ANALÍTICA
my_df2 = my_df.groupby('article_name').sum()
por_cant = my_df2.sort_values('quantity',ascending=False)
print(por_cant['quantity'].head(1))
# CLASE DE CONSULTA 11/7
# para obtener sólo el nombre del artículo
# print(por_cant['quantity'].head(1).index.tolist()[0])
article_name
HDD 413
Name: quantity, dtype: int64
# RESOLUCIÓN GRÁFICA
sns.displot(my_df, x='article_name')
plt.xticks(rotation=90)
plt.show()
# RESOLUCIÓN ANALÍTICA
my_df3 =(my_df.groupby('article_name').sum()).sort_values('total_amount', ascending=False).head(5)
print(my_df3['total_amount'])
article_name
Full Pc 538335.93
Notebook 251000.00
Smartphone 152250.00
Chair 69477.48
Tablet 48620.00
Name: total_amount, dtype: float64
# RESOLUCIÓN GRÁFICA
# OJO: No puedo hacer un análisis comparativo ni poner porcentajes porque
# no están todos los artículos en este df. Sólo puse los top 5
plt.pie(x=my_df3['total_amount'], labels=my_df3.index)
plt.show()
# RESOLUCIÓN ANALÍTICA
my_df4 = (my_df.groupby('seller_name').sum()).sort_values('total_amount', ascending=False)
print(my_df4[['quantity']+['total_amount']])
quantity total_amount
seller_name
Janel O'Curran 703 192832.47
Brockie Patience 441 142709.88
Oliviero Charkham 555 141329.76
Vasily Danilyuk 521 129157.55
Daisie Slograve 554 120520.11
Aveline Swanwick 629 118874.33
Arnold Kilkenny 583 94552.04
Kati Innot 512 83704.62
Jase Doy 582 80628.31
Ewell Peres 496 78144.32
Onida Cosely 535 77373.37
Milly Christoffe 442 61733.69
Tobin Roselli 519 56984.42
Cornie Wynrehame 523 52253.57
Cirilo Grandham 470 45009.40
# RESOLUCIÓN GRÁFICA
plt.bar(my_df4.index, my_df4['total_amount'])
plt.xticks(rotation=60)
plt.show()
# RESOLUCIÓN ANALÍTICA
my_df5 = (my_df.groupby('week').sum()).sort_values('total_amount',ascending=False)
print(my_df5)
quantity total_amount
week
1 2449 507458.81
2 2444 415364.44
3 2114 329140.03
4 1058 223844.56
# RESOLUCIÓN GRÁFICA
plt.bar(my_df5.index,my_df5['total_amount'])
plt.show()
# RESOLUCIÓN
# RESOLUCIÓN
# RESOLUCIÓN
Zona Experimental
#CONSULTA YAZHIRA
df_top_3_articles = my_df[(my_df['article_name'] == 'Full Pc') | (my_df['article_name'] == 'Notebook') | (my_df['article_name'] == 'Smartphone')]
df_top_3_articles = df_top_3_articles[['article_name','country_name','total_amount']]
df_top_3_articles = df_top_3_articles.groupby(['article_name','country_name'])['total_amount'].sum().reset_index()
print(df_top_3_articles)
article_name country_name total_amount
0 Full Pc Argentina 95751.45
1 Full Pc Bolivia 10639.05
2 Full Pc Brazil 134052.03
3 Full Pc Chile 2127.81
4 Full Pc Colombia 72345.54
5 Full Pc Costa Rica 23405.91
6 Full Pc El Salvador 40428.39
7 Full Pc Guatemala 27661.53
8 Full Pc Mexico 27661.53
9 Full Pc Peru 51067.44
10 Full Pc Uruguay 8511.24
11 Full Pc Venezuela 44684.01
12 Notebook Argentina 43000.00
13 Notebook Brazil 83000.00
14 Notebook Colombia 18000.00
15 Notebook Guatemala 17000.00
16 Notebook Honduras 14000.00
17 Notebook Mexico 44000.00
18 Notebook Peru 32000.00
19 Smartphone Argentina 13125.00
20 Smartphone Brazil 41475.00
21 Smartphone Chile 6300.00
22 Smartphone Colombia 27300.00
23 Smartphone Ecuador 7875.00
24 Smartphone El Salvador 11550.00
25 Smartphone Mexico 15225.00
26 Smartphone Peru 7875.00
27 Smartphone Uruguay 4725.00
28 Smartphone Venezuela 16800.00
plot_order = df_top_3_articles.groupby('country_name')['total_amount'].sum().sort_values(ascending=False).index.values
sns.catplot(y='total_amount',x='country_name',hue='article_name',data=df_top_3_articles,palette='rocket',kind='bar')
plt.xticks(rotation=90)
plt.title('Income generated by top 3 selled articles per Country')
plt.ylabel('Country')
plt.xlabel('Income ($)')
plt.show()
print(plot_order)
['Brazil' 'Argentina' 'Colombia' 'Peru' 'Mexico' 'Venezuela' 'El Salvador'
'Guatemala' 'Costa Rica' 'Honduras' 'Uruguay' 'Bolivia' 'Chile' 'Ecuador']
for i in range(len(my_df.index)):
article = df_articles.loc[my_df.loc[i]['article_id']]['article_name']
#my_df.loc[fila(i)][columna ('article_name')] Sintáxis para obtener el indice del recorrido en la tabla de my_df de 3 columnas y acceder al dato o nombre del artículo
my_df.loc[i,'article_name'] = article
#manejo de la misma sintáxis para total amount
my_df.loc[i,'total_amount'] = df_articles.loc[my_df.loc[i]['article_id']]['unit_price']* my_df.loc[i,'quantity']
#Elimino las columnas que no se necesitan
my_df.drop(['order_id','article_id','seller_id'], axis='columns', inplace=True)
print(my_df)