# 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 13.9 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')
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)
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
5 20020 Chair 335.64
6 20021 Modem 67.50
7 20022 Range Extender 20.45
8 20023 Notebook 1000.00
9 20024 Netbook 145.00
10 20025 HDD 54.62
11 20026 SDD 22.00
12 20027 Ram Memory 35.95
13 20028 Motherboard 138.38
14 20029 Mouse 30.30
15 20030 Fan Cooler 4.25
16 20031 Webcam 20.07
17 20032 Keyboard 22.60
18 20033 Headphones 23.30
19 20034 Scanner 185.00
20 20035 Case 37.90
21 20036 Video Card 131.50
22 20037 CPU 139.62
23 20038 Power Supply 43.95
24 20039 Water Cooling 67.50
25 20040 Heatsink 10.00
26 20041 Usb Cable 2.95
27 20042 Sata Cable 2.14
28 20043 Pci Express Port 10.12
29 20044 Wi-Fi Card 59.61
30 20045 Mesh Wi-Fi X 2 32.50
# VENDEDORES
df_sellers = pd.read_excel('/work/data/sellers.xlsx', index_col=0)
print(df_sellers)
seller_name
seller_id
1 Aveline Swanwick
2 Jase Doy
3 Oliviero Charkham
4 Cornie Wynrehame
5 Ewell Peres
6 Milly Christoffe
7 Kati Innot
8 Tobin Roselli
9 Onida Cosely
10 Cirilo Grandham
11 Vasily Danilyuk
12 Brockie Patience
13 Arnold Kilkenny
14 Janel O'Curran
15 Daisie Slograve
# 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')
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
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')
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
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')
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
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_orders
my_df = df_orders.copy()
# Cambio el índice del df_articles
df_articles.set_index('article_id', inplace=True)
print(df_articles.head())
article_name unit_price
article_id
20015 Smartphone 525.00
20016 Full Pc 2127.81
20017 Monitor 230.00
20018 Tablet 130.00
20019 Desk 130.10
print(my_df.head())
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
# 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())
order_id week article_id quantity seller_id country_name article_name \
0 15024 1 20039 10 10 Peru 20039
1 15025 1 20029 15 5 Peru 20029
2 15026 1 20024 5 14 Bolivia 20024
3 15027 1 20018 9 14 Brazil 20018
4 15028 1 20035 6 15 Mexico 20035
total_amount seller_name
0 20039 10
1 20029 5
2 20024 14
3 20018 14
4 20035 15
# 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']
print(my_df.head())
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
article_name total_amount seller_name
0 Water Cooling 675.0 Cirilo Grandham
1 Mouse 454.5 Ewell Peres
2 Netbook 725.0 Janel O'Curran
3 Tablet 1170.0 Janel O'Curran
4 Case 227.4 Daisie Slograve
# elimino las columnas que no necesito
my_df.drop(['order_id', 'article_id','seller_id'], axis='columns', inplace=True)
print(my_df.head())
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
#my_df.to_csv("dataset_depurado_y_filtrado.csv")
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))
mes ventas costos
0 ene 10 7
1 feb 20 16
2 mar 30 25
3 abr 15 12
# 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))
article_name
HDD 413
Name: quantity, dtype: int64
# RESOLUCIÓN GRÁFICA
sns.displot(my_df, x='article_name', kde=True)
plt.xticks(rotation=90)
plt.title('Cantidad de artículos vendidos', size = 16)
plt.ylabel("Cantidad en unidades")
plt.xlabel("")
plt.show()
# RESOLUCIÓN ANALÍTICA
my_df3 = (my_df.groupby('article_name').sum()).sort_values('total_amount', ascending=False).head(5)
rename_art_names = {"article_name": "Artículo", "total_amount": "Ganancia",}
rename_art = my_df3.reset_index()
rename_art = rename_art.rename(columns=rename_art_names)
rename_art['Ganancia'] = rename_art['Ganancia'].apply(lambda x: f"${x:.1f}")
print(rename_art[['Artículo', 'Ganancia']])
Artículo Ganancia
0 Full Pc $538335.9
1 Notebook $251000.0
2 Smartphone $152250.0
3 Chair $69477.5
4 Tablet $48620.0
# RESOLUCIÓN GRÁFICA
c=['steelblue','lightslategray','dodgerblue','lightskyblue', 'aliceblue']
plt.pie(x=my_df3['total_amount'],labels=my_df3.index, colors=c)
plt.title(' Los 5 artículos que mas ingresos generaron', size = 16)
plt.show()
# RESOLUCIÓN ANALÍTICA
df4 = (my_df.groupby('seller_name').sum()).sort_values('total_amount', ascending=False)
print(df4[['quantity']+['total_amount']])
quantity total_amount
seller_name
Janel O'Curran 703 192832.47
Brockie Patience 441 142709.88
Oliviero Charkham 555 141329.76
Vasily Danilyuk 521 129157.55
Daisie Slograve 554 120520.11
Aveline Swanwick 629 118874.33
Arnold Kilkenny 583 94552.04
Kati Innot 512 83704.62
Jase Doy 582 80628.31
Ewell Peres 496 78144.32
Onida Cosely 535 77373.37
Milly Christoffe 442 61733.69
Tobin Roselli 519 56984.42
Cornie Wynrehame 523 52253.57
Cirilo Grandham 470 45009.40
# RESOLUCIÓN GRÁFICA
plt.bar(df4.index, df4['total_amount'])
plt.xticks(rotation=60)
plt.title('Ganancia por vendedor', size = 16)
plt.ylabel("Ganancia u$")
plt.show()
# RESOLUCIÓN ANALÍTICA
df5=(my_df.groupby('week').sum()).sort_values('total_amount',ascending=False)
print(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(df5.index,df5['total_amount'])
plt.title('Ganancia por semana', size = 16)
plt.ylabel("Ganancia u$")
plt.xlabel('')
index = ['', '1 semana', '2 semana', '3 semana', '4 semana']
indice = np.arange(len(index))
plt.xticks(indice, index)
plt.xlabel("")
plt.savefig('ganancia_semana.png', dpi=300)
plt.show()
print(my_df.describe())
week quantity total_amount
count 1000.00000 1000.000000 1000.000000
mean 2.22400 8.065000 1475.807840
std 1.01531 4.326603 3705.470337
min 1.00000 1.000000 2.140000
25% 1.00000 4.000000 121.440000
50% 2.00000 8.000000 354.550000
75% 3.00000 12.000000 1160.000000
max 4.00000 15.000000 31917.150000
Total = my_df['total_amount'].sum()
print ("La ganancia total del mes en u$ es:",Total)
Total2 = my_df['quantity'].sum()
print ("La cantidad total de unidades vendidas es:",Total2)
Total3 = my_df['country_name'].drop_duplicates().count()
print ("La cantidad de países con los que se comercializó es :",Total3)
Total4 = my_df['seller_name'].drop_duplicates().count()
print ("La cantidad de vendedores es: ",Total4)
La ganancia total del mes en u$ es: 1475807.84
La cantidad total de unidades vendidas es: 8065
La cantidad de países con los que se comercializó es : 16
La cantidad de vendedores es: 15
# RESOLUCIÓN ANALÍTICA
grouped = my_df.groupby('country_name').agg({
"quantity": 'sum',
"article_name": 'count',
"total_amount": 'sum',
}).sort_values('total_amount',ascending=False)
renaming = {"quantity": "Cantidad", "article_name": "N° artículos.", "total_amount": "Ganancia",}
renamed = grouped.rename(columns=renaming)
renamed['Ganancia'] = renamed['Ganancia'].apply(lambda x: f"${x:.1f}")
print(renamed)
Cantidad N° artículos. Ganancia
country_name
Brazil 2515 315 $441271.9
Argentina 947 113 $205832.8
Colombia 881 111 $177514.3
Peru 1027 125 $161421.1
Mexico 846 101 $138620.0
Venezuela 320 37 $77684.5
El Salvador 111 16 $57391.3
Guatemala 202 29 $52579.2
Honduras 303 38 $36763.6
Costa Rica 145 19 $34606.5
Chile 231 28 $24661.0
Bolivia 181 19 $22682.8
Uruguay 92 12 $17843.1
Ecuador 129 18 $17475.3
Paraguay 123 17 $8195.1
Puerto Rico 12 2 $1265.4
# RESOLUCIÓN GRÁFICA
df6=(my_df.groupby('country_name').sum()).sort_values('total_amount',ascending=False)
plt.barh(df6.index,df6['total_amount'])
plt.title('Ganancia en dolares u$', size = 16)
plt.ylabel('')
plt.xlabel('')
plt.show()
# RESOLUCIÓN GRÁFICA
grouped["quantity"].plot(kind="barh")
plt.title('Cantidad de artículos vendidos (unidades)', size = 16)
plt.ylabel('')
plt.xlabel('')
plt.show()
df42 = my_df[['article_name', 'quantity']]
# ( article_name quantity
# 0 Water Cooling 10
# 0 Other 10
# 0 Phone 10
article_quantity_by_article_name = df42.groupby(['article_name']).agg({
"quantity": 'sum'
}).sort_values('quantity', ascending=False)
top_articles = article_quantity_by_article_name.head(10)
print('TOP ARTICLES')
print(top_articles)
TOP ARTICLES
quantity
article_name
HDD 413
Tablet 374
SDD 372
Mouse 322
Netbook 320
Ram Memory 293
Motherboard 291
Pci Express Port 291
Smartphone 290
Range Extender 281
plt.bar(top_articles.index,top_articles['quantity'])
plt.xticks(rotation=90)
plt.title('Artículos con mayor demanda', size = 16)
plt.ylabel('Unidades')
plt.xlabel('')
#grouped.to_csv("dataset_agrupado.csv")
print('BOTTOM ARTICLES')
bottom_articles = article_quantity_by_article_name.tail(10)
print(bottom_articles)
BOTTOM ARTICLES
quantity
article_name
Desk 223
Scanner 221
Mesh Wi-Fi X 2 213
Video Card 209
Monitor 208
Chair 207
Case 206
Fan Cooler 205
Keyboard 165
Wi-Fi Card 141
# RESOLUCIÓN GRÁFICA
plt.bar(bottom_articles.index,bottom_articles['quantity'])
plt.xticks(rotation=90)
plt.title('Artículos a enforcar la campaña publicitario', size = 16)
plt.ylabel('Unidades')
plt.xlabel('')
plt.show()