# 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 22.3.1 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
import matplotlib.pyplot as plt
import seaborn as sns
# Levanto los datos en 3 diferentes dataframes
# Articulos
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('\nBusqueda 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)
Busqueda 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('\nBusqueda 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)
Busqueda 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('\nBusqueda 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)
Busqueda 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
# https://pandas.pydata.org/docs/user_guide/indexing.html
# https://towardsdatascience.com/how-to-use-loc-and-iloc-for-selecting-data-in-pandas-bd09cb4c3d79
# https://stackoverflow.com/questions/28754603/indexing-pandas-data-frames-integer-rows-named-columns
my_df = df_orders.copy() # Shallow copy
# 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'])
# print(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[i]['article_id']]['article_name'])
article = df_articles.loc[my_df.loc[i]['article_id']]['article_name']
# print(article)
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']
# elimino 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]
# my_df.loc[:, 'quantity']
# my_df.loc[0, ['quantity','country_name']]
# my_df.loc[0:5, ['quantity','country_name']]
# my_df.iloc[:,1]
# my_df.iloc[0,[1,2]]
my_df.iloc[0:5,[1,2]]
quantityint64
country_nameobject
0
10
Peru
1
15
Peru
2
5
Bolivia
3
9
Brazil
4
6
Mexico
# RESOLUCIÓN ANALÍTICA
df1 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df1[['quantity','total_amount']].head())
quantity total_amount
article_name
HDD 413 $ 22,558.06
Tablet 374 $ 48,620.00
SDD 372 $ 8,184.00
Mouse 322 $ 9,756.60
Netbook 320 $ 46,400.00
# RESOLUCIÓN GRÁFICA
# Opción 1 - Count
# sns.countplot(my_df, x='article_name')
# Opción 2 - barplot
# sns.barplot(data=df7, x=df7.index, y='quantity')
# Opción 3 - barplot
xs = ["HDD", "Tablet", "SDD", "Mouse", "Netbook"]
ys = [413, 374, 372, 322, 320]
sns.barplot(x=xs, y=ys)
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(df2['total_amount'])
# print(df2)
# print()
# print(df2.index[0])
# print()
# print(df2.index[0])
# print(df2.iloc[0])
print()
for i in range(5):
print(df2.index[i])
print(df2.reset_index().iloc[i])
print()
# print()
# print(df2.reset_index())
article_name
Full Pc $ 538,335.93
Notebook $ 251,000.00
Smartphone $ 152,250.00
Chair $ 69,477.48
Tablet $ 48,620.00
Name: total_amount, dtype: float64
Full Pc
article_name Full Pc
week 70
quantity 253
total_amount $ 538,335.93
Name: 0, dtype: object
Notebook
article_name Notebook
week 69
quantity 251
total_amount $ 251,000.00
Name: 1, dtype: object
Smartphone
article_name Smartphone
week 74
quantity 290
total_amount $ 152,250.00
Name: 2, dtype: object
Chair
article_name Chair
week 56
quantity 207
total_amount $ 69,477.48
Name: 3, dtype: object
Tablet
article_name Tablet
week 90
quantity 374
total_amount $ 48,620.00
Name: 4, dtype: object
# RESOLUCIÓN GRÁFICA
plt.pie(x=df2['total_amount'], labels=df2.index, autopct='%1.2f%%')
plt.show()
# RESOLUCIÓN ANALÍTICA
df3 = my_df.groupby(by='seller_name').sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df3[['quantity'] + ['total_amount']].head(5))
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(df3.index, df3['total_amount'])
plt.xticks(rotation=90)
plt.show()
# RESOLUCIÓN ANALÍTICA
df4 = my_df.groupby(by='week').sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df4[['quantity'] + ['total_amount']])
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(df4.index, df4['total_amount'])
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
print('Paises con mayores ventas')
df5 = my_df.groupby(by='country_name').sum().sort_values('total_amount', ascending=False)
df5_arg_br = df5['total_amount'].head(2)
print(df5_arg_br)
print('Países Top 2 en ventas')
e = (0, 0.1)
c = ['green', 'deepskyblue']
plt.pie(x=df5_arg_br, radius=0.9, labels=df5_arg_br.index, explode=e, colors=c, autopct='%1.2f%%')
plt.show()
# df5_1 = my_df.loc[(my_df['country_name'] == 'Brazil') | (my_df['country_name'] == 'Argentina')].sort_values('total_amount', ascending=False)
# print(df5_1.head())
print('\nTop 5 Productos más vendidos en Brasil')
df5_1 = my_df.loc[my_df['country_name'] == 'Brazil'].sort_values('total_amount', ascending=False)
# print(df5_1.head())
df5_2 = df5_1.groupby(by='article_name').sum().sort_values('total_amount', ascending=False)
print(df5_2.head())
print('\nTop 5 Productos más vendidos en Argentina')
df5_3 = my_df.loc[my_df['country_name'] == 'Argentina'].sort_values('total_amount', ascending=False)
# print(df5_3.head())
df5_4 = df5_3.groupby(by='article_name').sum().sort_values('total_amount', ascending=False)
print(df5_4.head())
print('Top 5 productos más vendidos en Brazil y Argentina')
plt.subplot(1,2,1)
df5_br = df5_2.sort_values('quantity', ascending=False).head()
plt.bar(df5_br.index, df5_br['quantity'], color='green')
plt.xticks(rotation=90, fontsize=9)
plt.title("Brasil")
plt.subplot(1,2,2)
df5_ar = df5_4.sort_values('quantity', ascending=False).head()
plt.bar(df5_ar.index, df5_ar['quantity'], color='deepskyblue')
plt.xticks(rotation=90, fontsize=9)
plt.title("Argentina")
plt.show()
# print('\nPara verificar resultados de las tablas')
# print(df5['total_amount'].head(2))
# print('\nTotal Ventas en Brasil:')
# print(df5_1['total_amount'].sum())
# print('\nTotal Ventas en Argentina:')
# print(df5_3['total_amount'].sum())
Paises con mayores ventas
country_name
Brazil $ 441,271.85
Argentina $ 205,832.78
Name: total_amount, dtype: float64
Países Top 2 en ventas
Top 5 Productos más vendidos en Brasil
week quantity total_amount
article_name
Full Pc 17 63 $ 134,052.03
Notebook 20 83 $ 83,000.00
Smartphone 19 79 $ 41,475.00
Chair 32 112 $ 37,591.68
Tablet 41 156 $ 20,280.00
Top 5 Productos más vendidos en Argentina
week quantity total_amount
article_name
Full Pc 10 45 $ 95,751.45
Notebook 16 43 $ 43,000.00
CPU 23 104 $ 14,520.48
Smartphone 5 25 $ 13,125.00
Netbook 8 39 $ 5,655.00
Top 5 productos más vendidos en Brazil y Argentina
# RESOLUCIÓN
# Evolución de Ventas por producto.
# Tomar 2 países y 'week' como variable categórica
# Resolución Analítica y Gráfica
print('Evolución de Ventas por productos en Argentina y Brasil')
df6 = my_df.loc[(my_df['country_name'] == 'Brazil') | (my_df['country_name'] == 'Argentina')].sort_values(['country_name', 'article_name', 'week'])
df6_1 = df6[['country_name', 'article_name', 'week', 'total_amount']]
print(df6_1)
print('\nEvolución de Ventas por productos en Argentina')
df6_2 = df6_1[df6_1['country_name'] == 'Argentina'].groupby(['article_name', 'week']).agg({'total_amount':'sum'})
print(df6_2)
print('\nEvolución de Ventas por productos en Brasil')
df6_3 = df6_1[df6_1['country_name'] == 'Brazil'].groupby(['article_name', 'week']).agg({'total_amount':'sum'})
print(df6_3)
Evolución de Ventas por productos en Argentina y Brasil
country_name article_name week total_amount
79 Argentina CPU 1 $ 698.10
266 Argentina CPU 1 $ 1,535.82
393 Argentina CPU 2 $ 1,815.06
415 Argentina CPU 2 $ 1,675.44
761 Argentina CPU 3 $ 2,094.30
.. ... ... ... ...
377 Brazil Wi-Fi Card 2 $ 119.22
390 Brazil Wi-Fi Card 2 $ 178.83
458 Brazil Wi-Fi Card 2 $ 119.22
547 Brazil Wi-Fi Card 2 $ 298.05
693 Brazil Wi-Fi Card 3 $ 476.88
[428 rows x 4 columns]
Evolución de Ventas por productos en Argentina
total_amount
article_name week
CPU 1 $ 2,233.92
2 $ 3,490.50
3 $ 5,165.94
4 $ 3,630.12
Case 1 $ 568.50
... ...
Water Cooling 1 $ 337.50
2 $ 877.50
3 $ 472.50
Webcam 2 $ 200.70
Wi-Fi Card 2 $ 715.32
[67 rows x 1 columns]
Evolución de Ventas por productos en Brasil
total_amount
article_name week
CPU 1 $ 3,769.74
2 $ 5,165.94
3 $ 2,513.16
Case 1 $ 454.80
2 $ 606.40
... ...
Webcam 3 $ 240.84
4 $ 140.49
Wi-Fi Card 1 $ 1,013.37
2 $ 715.32
3 $ 476.88
[111 rows x 1 columns]
# RESOLUCIÓN
# Mejor vendedor/producto. Mostrar importe/cantidad. Comparar 2 países (variable categórica)
# Resolución Analítica y Gráfica
# print('\nInformación de vendedores por pr')
# df7 = df6[['country_name', 'seller_name', 'article_name', 'quantity', 'total_amount']]
# # print(df7)
# df7_1 = df7.sort_values(['country_name', 'seller_name', 'article_name'], ascending=True)
# # print(df7_1)
# importe = (df7_1['total_amount']/df7_1['quantity'])
# # print(importe)
# df7_1.insert(4, 'unit_price', (df7_1['total_amount']/df7_1['quantity']))
# print(df7_1)
# df7_2 = df7_1.set_index(["country_name", "seller_name", "article_name", "total_amount"])
# print(df7_2)
# df7_3 = df7_2.groupby(['seller_name', 'article_name']).sum()
# print(df7_3)
print('\nInformación de vendedores por producto')
df7 = df6[['country_name', 'article_name', 'seller_name', 'quantity', 'total_amount']]
# print(df7)
importe = (df7['total_amount']/df7['quantity'])
df7.insert(4, 'unit_price', (df7['total_amount']/df7['quantity']))
df7_1 = df7.sort_values(['article_name', 'seller_name'], ascending=True)
# print(df7_1)
df7_2 = df7_1.set_index(["article_name"])
# print(df7_2)
df7_3 = df7_2.groupby(["article_name", "seller_name"]).sum()
print(df7_3)
Información de vendedores por producto
quantity unit_price total_amount
article_name seller_name
CPU Arnold Kilkenny 40 $ 558.48 $ 5,584.80
Brockie Patience 12 $ 139.62 $ 1,675.44
Cirilo Grandham 5 $ 139.62 $ 698.10
Cornie Wynrehame 13 $ 139.62 $ 1,815.06
Daisie Slograve 15 $ 139.62 $ 2,094.30
... ... ... ...
Wi-Fi Card Janel O'Curran 12 $ 119.22 $ 715.32
Kati Innot 8 $ 119.22 $ 476.88
Milly Christoffe 2 $ 59.61 $ 119.22
Oliviero Charkham 12 $ 119.22 $ 715.32
Onida Cosely 5 $ 59.61 $ 298.05
[269 rows x 3 columns]
df8 = my_df[my_df['country_name'] == 'Brazil']
vendedores_pais = df8.groupby('seller_name').sum().sort_values('total_amount', ascending=False)
vendedores_pais.head()
weekint64
quantityint64
Arnold Kilkenny
47
184
Kati Innot
52
151
Tobin Roselli
54
211
Daisie Slograve
60
226
Aveline Swanwick
66
227
plt.bar(vendedores_pais.index,vendedores_pais['total_amount'],
color = ['green' if x in vendedores_pais.index[0:5] else 'blue' for x in vendedores_pais.index]) #Color verde para los mejores 5
plt.xticks(rotation = 90)
plt.title("Desempeño vendedores del país que más compra")
plt.xlabel("Vendedores")
plt.ylabel("Total de Ventas")
plt.show()
df_brazil = my_df[my_df['country_name'] == 'Brazil']
print(df_brazil[['seller_name','total_amount', 'quantity']].groupby('seller_name').sum().sort_values('total_amount', ascending=False))
print()
df_brazil_bars = df_brazil[['seller_name','total_amount']].groupby('seller_name').sum('total_amount').sort_values('total_amount', ascending=False)
print(df_brazil_bars)
print()
df_brazil_line = df_brazil[['seller_name','quantity']].groupby('seller_name').sum('quantity').sort_values('quantity', ascending=False).reset_index()
print(df_brazil_line)
fig, ax1 = plt.subplots()
# ax1: axes1
# sns.barplot(data = df_brazil_bars, x='seller_name', y='total_amount', ax=ax1, color='C3')
sns.barplot(data = df_brazil_bars, x = df_brazil_bars.index, y='total_amount', ax=ax1, color='C3')
# ax: axes
plt.xticks(rotation=90)
ax2 = ax1.twinx()
# ax2: axes2 = ax1.twinx()
sns.lineplot(data = df_brazil_line, x='seller_name', y='quantity', ax=ax2, color='C11')
plt.xticks(rotation=90)
plt.title('Top sellers in Brazil')
ax1.set_xlabel("Seller Name")
ax1.set_ylabel("Income ($)")
ax2.set_ylabel("Quantity (line)")
plt.show()
total_amount quantity
seller_name
Daisie Slograve $ 65,283.28 226
Aveline Swanwick $ 58,771.48 227
Arnold Kilkenny $ 47,243.54 184
Kati Innot $ 32,087.32 151
Tobin Roselli $ 31,997.93 211
Janel O'Curran $ 31,562.86 182
Onida Cosely $ 29,354.31 206
Jase Doy $ 28,493.25 149
Vasily Danilyuk $ 27,495.77 124
Milly Christoffe $ 21,247.38 161
Cirilo Grandham $ 21,061.74 158
Ewell Peres $ 15,253.22 91
Oliviero Charkham $ 14,951.72 195
Brockie Patience $ 10,756.96 125
Cornie Wynrehame $ 5,711.09 125
total_amount
seller_name
Daisie Slograve $ 65,283.28
Aveline Swanwick $ 58,771.48
Arnold Kilkenny $ 47,243.54
Kati Innot $ 32,087.32
Tobin Roselli $ 31,997.93
Janel O'Curran $ 31,562.86
Onida Cosely $ 29,354.31
Jase Doy $ 28,493.25
Vasily Danilyuk $ 27,495.77
Milly Christoffe $ 21,247.38
Cirilo Grandham $ 21,061.74
Ewell Peres $ 15,253.22
Oliviero Charkham $ 14,951.72
Brockie Patience $ 10,756.96
Cornie Wynrehame $ 5,711.09
seller_name quantity
0 Aveline Swanwick 227
1 Daisie Slograve 226
2 Tobin Roselli 211
3 Onida Cosely 206
4 Oliviero Charkham 195
5 Arnold Kilkenny 184
6 Janel O'Curran 182
7 Milly Christoffe 161
8 Cirilo Grandham 158
9 Kati Innot 151
10 Jase Doy 149
11 Brockie Patience 125
12 Cornie Wynrehame 125
13 Vasily Danilyuk 124
14 Ewell Peres 91