!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 28.7 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 22.3.1 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 # levantar excel
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
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'])
for i in range(max(my_df.count())):
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']
# 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[:, [1,2]]
my_df.iloc[0:6, [1,2]]
quantityint64
country_nameobject
0
10
Peru
1
15
Peru
2
5
Bolivia
3
9
Brazil
4
6
Mexico
5
6
Peru
# RESOLUCIÓN ANALÍTICA
df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False)
pd.options.display.float_format= '$ {:,.2f}'.format
print(df7[['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
sns.barplot(data=df7, x=df7.index, y='quantity')
plt.xticks(rotation=90)
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)
print(df2['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
Name: total_amount, dtype: float64
# RESOLUCIÓN GRÁFICA
my_explode = [0.02, 0, 0, 0, 0]
plt.pie(x=df2['total_amount'], labels=df2.index, autopct='%1.2f%%', explode = my_explode)
plt.show()
# 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']].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.barh(df4.index, df4['total_amount'], align='center', color = ['red' if x in df4.index[0] else 'blue' for x in df4.index], edgecolor='none')
vendedores = df4.index
cantidad = df4['total_amount'].values
for i in range(len(vendedores)):
etiqueta = '$' + str(int(cantidad[i]))
plt.text( s=etiqueta, x=cantidad[i] + 15000 ,y=vendedores[i], ha='center')
plt.gca().spines['bottom'].set_visible(False)
plt.gca().spines['left'].set_visible(False)
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.gca().invert_yaxis()
plt.xlabel('')
plt.xticks([])
plt.ylabel('')
plt.show()
# RESOLUCIÓN ANALÍTICA
df5 = my_df.groupby(by='week').sum().sort_values('total_amount', ascending=False)
pd.options.display.float_format = '$ {:,.2f}'.format
print(df5[['quantity'] + ['total_amount']])
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.figure()
plt.bar(df5.index, df5['total_amount'], align='center')
ing_week = df5['total_amount'].values
for i,n in enumerate(ing_week):
etiqueta = '$' + str(int(n))
plt.text( s=etiqueta, x=(i+1) ,y=df5['total_amount'][i+1] + 10000, ha='center')
plt.gca().spines['bottom'].set_visible(False)
plt.gca().spines['left'].set_visible(False)
plt.gca().spines['top'].set_visible(False)
plt.gca().spines['right'].set_visible(False)
plt.xlabel('')
plt.xticks(range(1, 5, 1))
plt.yticks([])
plt.ylabel(ylabel='')
plt.suptitle('Variaciones de ventas a lo largo del mes')
plt.show()
# RESOLUCIÓN ANALÍTICA
df6 = my_df.groupby(by='country_name').sum().sort_values('total_amount', ascending=False).head(5)
pd.options.display.float_format = '$ {:,.2f}'.format
print(df6[['quantity'] + ['total_amount']])
quantity total_amount
country_name
Brazil 2515 $ 441,271.85
Argentina 947 $ 205,832.78
Colombia 881 $ 177,514.29
Peru 1027 $ 161,421.12
Mexico 846 $ 138,619.99
# RESOLUCIÓN ANALÍTICA
df_brazil = my_df[my_df['country_name'] == 'Brazil']
df_argentina = my_df[my_df['country_name'] == 'Argentina']
df_art_bra = df_brazil.groupby(by='article_name').sum().sort_values('quantity', ascending=False).head(5)
df_art_arg = df_argentina.groupby(by='article_name').sum().sort_values('quantity', ascending=False).head(5)
print("Artículos más vendidos en Argentina:\n", df_art_arg[['quantity']])
print("\n\n")
print("Artículos más vendidos en Brazil:\n",df_art_bra[['quantity']])
Artículos más vendidos en Argentina:
quantity
article_name
CPU 104
SDD 73
HDD 68
Range Extender 58
Fan Cooler 47
Artículos más vendidos en Brazil:
quantity
article_name
Tablet 156
HDD 119
SDD 117
Chair 112
Pci Express Port 105
# RESOLUCIÓN
df_week_bra = df_brazil[df_brazil['article_name'] == 'Tablet'].groupby(by='week').sum()
df_week_arg = df_argentina[df_argentina['article_name'] == 'CPU'].groupby(by='week').sum()
labels = df_week_arg.index
print(labels)
x = np.arange(len(labels))
width = 0.35
fig, ax = plt.subplots()
rects1 = ax.bar(x - width/2, df_week_arg['quantity'], width, label='Argentina')
rects2 = ax.bar(x + width/2, df_week_bra['quantity'], width, label='Brazil')
ax.set_ylabel('quantity')
ax.set_title('Variación de ventas del artículo más vendido a lo largo del mes')
ax.set_xticks(x, labels)
ax.legend()
ax.bar_label(rects1, padding=3)
ax.bar_label(rects2, padding=3)
fig.tight_layout()
plt.show()
Int64Index([1, 2, 3, 4], dtype='int64', name='week')