# A veces necesitamos instalar nuevas librerías en nuestros proyectos
!pip install openpyxl==3.0.10
Requirement already satisfied: openpyxl==3.0.10 in /root/venv/lib/python3.9/site-packages (3.0.10)
Requirement already satisfied: et-xmlfile in /root/venv/lib/python3.9/site-packages (from openpyxl==3.0.10) (1.1.0)
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 openpyxl # levantar excel
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'])
# 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 nulls por columna')
print(df_articles.isnull().sum())
print('\nFormato de los datos por columna')
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 nulls por columna
article_id 0
article_name 0
unit_price 0
dtype: int64
Formato de los datos por columna
article_id int64
article_name object
unit_price object
dtype: object
# 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('\nBúsqueda de valores nulls por columna')
print(df_sellers.isnull().sum())
print('\nFormato de los datos por columna')
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 nulls por columna
seller_name 0
dtype: int64
Formato de los datos por columna
seller_name object
dtype: object
# 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 nulls por columna')
print(df_orders.isnull().sum())
print('\nFormato de los datos por columna')
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 nulls por columna
order_id 0
week 0
article_id 0
quantity 0
seller_id 0
country_name 0
dtype: int64
Formato de los datos por columna
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
my_df = df_orders.copy() # shallow copy o copia superficial (otro Objeto alojado en la memoria)
# 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'])
# 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']
# elimimo las columnas que no necesito del df
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
print(my_df['article_name'].value_counts())
HDD 47
Netbook 45
SDD 45
Tablet 40
Usb Cable 39
Sata Cable 38
Pci Express Port 37
Range Extender 36
Smartphone 35
Mouse 34
Full Pc 34
Headphones 34
Power Supply 34
Heatsink 34
Motherboard 33
Water Cooling 32
Ram Memory 31
Video Card 31
Notebook 30
Modem 29
CPU 29
Desk 28
Webcam 28
Mesh Wi-Fi X 2 28
Monitor 26
Case 26
Fan Cooler 25
Scanner 24
Chair 24
Keyboard 22
Wi-Fi Card 22
Name: article_name, dtype: int64
# RESOLUCIÓN GRÁFICA
sns.displot(my_df, x='article_name',hue='article_name',palette='terrain')
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(my_df[['article_name'] + ['total_amount']].groupby(['article_name']).sum().sort_values('total_amount', ascending=False).head(5))
total_amount
article_name
Full Pc $ 538,335.93
Notebook $ 251,000.00
Smartphone $ 152,250.00
Chair $ 69,477.48
Tablet $ 48,620.00
# RESOLUCIÓN GRÁFICA
plt.pie(x=df2['total_amount'], labels=df2.index,autopct='%1.1f%%')
plt.xticks()
plt.show()
# 'article_name' es el index
# 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']])
print(df4[['quantity'] + ['total_amount']].head(5))
# 'seller_name' es el index
quantity total_amount
seller_name
Janel O'Curran 703 $ 192,832.47
Brockie Patience 441 $ 142,709.88
Oliviero Charkham 555 $ 141,329.76
Vasily Danilyuk 521 $ 129,157.55
Daisie Slograve 554 $ 120,520.11
# RESOLUCIÓN GRÁFICA
plt.bar(df4.index, df4['total_amount'],color='blueviolet')
plt.xticks(rotation=60)
plt.show()
# 'seller_name' es el index
# 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
quantity total_amount
week
1 2449 $ 507,458.81
2 2444 $ 415,364.44
3 2114 $ 329,140.03
4 1058 $ 223,844.56
# RESOLUCIÓN GRÁFICA
plt.bar(df5.index, df5['total_amount'],color='darkviolet')
plt.show()
# 'week' es el index
# RESOLUCIÓN
# Ventas filtrado por país. Comparar 2 países
# Cuál es el producto que más se vende, en qué cantidad
# Resolución Analítica y Gráfica
#Resolucion Analitica
print('PRODUCTOS MAS VENDIDOS')
df6 = my_df.groupby(['country_name']).sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(my_df[['article_name']+['quantity']+ ['total_amount']].groupby(['article_name']).sum().sort_values('total_amount', ascending=False).head(5))
print('PAISES CON MAYORES VENTAS')
df7= my_df.groupby(['country_name']).sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df7[['quantity'] + ['total_amount']].head(2))
df8=df7[['quantity'] + ['total_amount']].head(2)
PRODUCTOS MAS VENDIDOS
quantity total_amount
article_name
Full Pc 253 $ 538,335.93
Notebook 251 $ 251,000.00
Smartphone 290 $ 152,250.00
Chair 207 $ 69,477.48
Tablet 374 $ 48,620.00
PAISES CON MAYORES VENTAS
quantity total_amount
country_name
Brazil 2515 $ 441,271.85
Argentina 947 $ 205,832.78
#Resolucion Grafica
sns.barplot(df8.index, df8['quantity'],palette='magma')
plt.xticks(rotation=60)
plt.title("Paises con mayores ventas")
plt.xlabel("País")
plt.ylabel("Cantidad")
plt.yticks(np.arange(0,2800,300))
plt.show()
plt.pie(x=df6['total_amount'], labels=df6.index,autopct='%1.1f%%')
plt.show()
/shared-libs/python3.9/py/lib/python3.9/site-packages/seaborn/_decorators.py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
warnings.warn(
# RESOLUCIÓN
# Evolución de Ventas por producto.
# Tomar 2 países y 'week' como variable categórica
# Resolución Analítica y Gráfica
df9=my_df[['week','article_name','country_name','quantity','total_amount']]
df9=df9.groupby(['country_name','article_name'])['quantity','total_amount','week'].sum().reset_index().sort_values(by='total_amount',ascending=False).head(3)
print(df9)
country_name article_name quantity total_amount week
45 Brazil Full Pc 63 $ 134,052.03 17
5 Argentina Full Pc 45 $ 95,751.45 10
56 Brazil Notebook 83 $ 83,000.00 20
<ipython-input-19-61a4e457a7e8>:8: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.
df9=df9.groupby(['country_name','article_name'])['quantity','total_amount','week'].sum().reset_index().sort_values(by='total_amount',ascending=False).head(3)
#Resolucion Grafica
sns.barplot(x='week', y='total_amount', data = df9, color='#69b3a2')
plt.xticks(rotation=90)
plt.xticks(rotation=90)
plt.title('Evolucion de ventas')
plt.xlabel("week")
plt.ylabel("Total Amount")
plt.show()
# RESOLUCIÓN
# Mejor vendedor/producto. Mostrar importe/cantidad. Comparar 2 países (variable categórica)
# RESOLUCIÓN ANALÍTICA
df10=my_df[['seller_name','country_name','week', 'quantity', 'total_amount']]
df10=df10[df10['country_name']=='Brazil']
df10=df10.groupby(['seller_name','country_name'])['quantity','total_amount','week'].sum().reset_index().sort_values(by='total_amount',ascending=False).head()
print(df10)
<ipython-input-21-94783b7fc84c>:8: FutureWarning: Indexing with multiple keys (implicitly converted to a tuple of keys) will be deprecated, use a list instead.
df10=df10.groupby(['seller_name','country_name'])['quantity','total_amount','week'].sum().reset_index().sort_values(by='total_amount',ascending=False).head()
seller_name country_name quantity total_amount week
5 Daisie Slograve Brazil 226 $ 65,283.28 60
1 Aveline Swanwick Brazil 227 $ 58,771.48 66
0 Arnold Kilkenny Brazil 184 $ 47,243.54 47
9 Kati Innot Brazil 151 $ 32,087.32 52
13 Tobin Roselli Brazil 211 $ 31,997.93 54
# RESOLUCIÓN Grafica
sns.barplot(data=df10,x='quantity',y='total_amount',hue='seller_name',dodge=False,)
plt.xticks(rotation=45)
plt.title('MEJORES VENDEDORES DE BRASIL')
plt.legend()
plt.show()