# 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 15.1 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
# ARTICULOS
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)
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
de_sellers = pd.read.excel('/work/data/sellers.xlsx')
print (df_sellers)
Execution error
AttributeError: module 'pandas' has no attribute 'read'
# entonces copiamos y pasamos x google
# encuentro q tngo q instalar un paquete
# una libreria nueva que no viene con deepnotes
# necesito salir del nterprete de pytin con ! antes de los import
#!pip install openpyxl==3.0.10
df_sellers = pd.read_excel('/work/data/sellers.xlsx')
print (df_sellers)
seller_id seller_name
0 1 Aveline Swanwick
1 2 Jase Doy
2 3 Oliviero Charkham
3 4 Cornie Wynrehame
4 5 Ewell Peres
5 6 Milly Christoffe
6 7 Kati Innot
7 8 Tobin Roselli
8 9 Onida Cosely
9 10 Cirilo Grandham
10 11 Vasily Danilyuk
11 12 Brockie Patience
12 13 Arnold Kilkenny
13 14 Janel O'Curran
14 15 Daisie Slograve
# Me conviene usar el id como indice
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
# ORDENES
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('\n Formato del dataframe')
print(df_articles.shape)
print('\n Busqueda de valores nulos por columna')
print(df_articles.isnull().sum())
print('\n Formato 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)
Busqueda 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('\n Formato del dataframe')
print(df_sellers.shape)
print('\n Busqueda de valores nulos por columna')
print(df_sellers.isnull().sum())
print('\n Formato 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)
Busqueda 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('\n Formato del dataframe')
print(df_orders.shape)
print('\n Busqueda de valores nulos por columna')
print(df_orders.isnull().sum())
print('\n Formato 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)
Busqueda 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()
print(my_df)
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]
# habia q cambiar el indice del df articulos
df_articles.set_index('article_id', inplace=True)
print (df_articles)
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
20020 Chair 335.64
20021 Modem 67.50
20022 Range Extender 20.45
20023 Notebook 1000.00
20024 Netbook 145.00
20025 HDD 54.62
20026 SDD 22.00
20027 Ram Memory 35.95
20028 Motherboard 138.38
20029 Mouse 30.30
20030 Fan Cooler 4.25
20031 Webcam 20.07
20032 Keyboard 22.60
20033 Headphones 23.30
20034 Scanner 185.00
20035 Case 37.90
20036 Video Card 131.50
20037 CPU 139.62
20038 Power Supply 43.95
20039 Water Cooling 67.50
20040 Heatsink 10.00
20041 Usb Cable 2.95
20042 Sata Cable 2.14
20043 Pci Express Port 10.12
20044 Wi-Fi Card 59.61
20045 Mesh Wi-Fi X 2 32.50
# 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'])
print(my_df)
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
article_name
0 20039
1 20029
2 20024
3 20018
4 20035
.. ...
995 20021
996 20040
997 20040
998 20018
999 20026
[1000 rows x 7 columns]
# necesito el precio unitario
my_df = my_df.assign(total_amount = my_df['article_id'])
my_df = my_df.assign(seller_name = my_df['seller_id'])
# como reemplazo los valores en en nuevo df
# ejemplo id article x nombre article
# df_article[?][article_name] una vez x c/u de los registros =>z for
for i in range(len(my_df.index)):
# len ...devuelve cantidad de registros
article = df_articles.loc[my_df.loc[i]['article_name']]['article_name']
# reemplazo 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'] * # unit_price
# unite_pfice ... df_articles.loc[my_df.loc[i]['total_amount']]['unit_price']
# my_df.loc[i,'total_amount']= my_df.loc[i,'quantity'] * df
my_df.loc[i,'total_amount'] = my_df.loc[i,'quantity'] * df_articles.loc[my_df.loc[i]['total_amount']]['unit_price']
# modificar la columna 'seller_name'
my_df.loc[i,'seller_name'] = df_sellers.loc[my_df.loc[i]['seller_name']]['seller_name']
print(my_df)
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
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
.. ... ... ...
995 Modem 67.5 Kati Innot
996 Heatsink 150.0 Daisie Slograve
997 Heatsink 20.0 Vasily Danilyuk
998 Tablet 1820.0 Vasily Danilyuk
999 SDD 264.0 Onida Cosely
[1000 rows x 9 columns]
# 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))
article_name
HDD 413
Name: quantity, dtype: int64
# RESOLUCIÓN GRÁFICA ---- estilooo
sns.displot(my_df, x = 'article_name', color='tab:purple')
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 analisis comparativo ni poner porcentaje porque
# no están todos los articulos en esde df. Solo puse los top 5
c=['gold','purple','blue','yellowgreen','lightskyblue']
plt.pie(x=my_df3['total_amount'], labels=my_df3.index, colors = c)
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'], color= 'gold')
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'], color='yellowgreen')
# c=['gold','purple','blue','yellowgreen']
# plt.pie(my_df5.index, my_df5['total_amount'], labels=my_df5.index, color=c, autopct ='%1,2f%%')
plt.show()
5 paises que mas vendieron en dinero
# RESOLUCIÓN cantry name ...otra con correlacion entre vbles categoricas
my_df6 = (my_df.groupby('country_name').sum()).sort_values('total_amount', ascending=False).head(5)
print(my_df6)
week quantity total_amount
country_name
Brazil 717 2515 441271.85
Argentina 241 947 205832.78
Colombia 230 881 177514.29
Peru 266 1027 161421.12
Mexico 237 846 138619.99
5 paises que mas vendieron en cantidades
# RESOLUCIÓN
my_df7 = (my_df.groupby('country_name').sum()).sort_values('quantity', ascending=False).head(5)
print(my_df7)
week quantity total_amount
country_name
Brazil 717 2515 441271.85
Peru 266 1027 161421.12
Argentina 241 947 205832.78
Colombia 230 881 177514.29
Mexico 237 846 138619.99
Nombre del vendedor top
# RESOLUCIÓN
my_df8 = my_df.groupby('seller_name').sum()
por_mont = my_df8.sort_values('total_amount', ascending= False)
print(por_mont['total_amount'].head(1))
seller_name
Janel O'Curran 192832.47
Name: total_amount, dtype: float64