# 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.
# 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 nuls 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 nuls 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 nuls 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 nuls 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 nuls 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 nuls 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 indice 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())):
# SINTAXIS: df_articles.loc[indice][columna]
# [indice] va a ser el dato que obtengo de my_df.loc[i]['article_id']
# [indice] -> [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)
# 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']
# 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]
# RESOLUCIÓN ANALÍTICA
print(my_df['article_name'].value_counts()) # cuenta valores únicos
HDD 47
Netbook 45
SDD 45
Tablet 40
Usb Cable 39
Sata Cable 38
Pci Express Port 37
Range Extender 36
Smartphone 35
Full Pc 34
Power Supply 34
Mouse 34
Heatsink 34
Headphones 34
Motherboard 33
Water Cooling 32
Ram Memory 31
Video Card 31
Notebook 30
Modem 29
CPU 29
Mesh Wi-Fi X 2 28
Desk 28
Webcam 28
Case 26
Monitor 26
Fan Cooler 25
Chair 24
Scanner 24
Keyboard 22
Wi-Fi Card 22
Name: article_name, dtype: int64
# RESOLUCIÓN GRÁFICA
sns.displot(my_df, x='article_name')
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'])
# 'article_name' es el index
# print(df2) # agrupa (y suma) sólo variables numéricas
# SINTAXIS ALTERNATIVA
# 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))
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
plt.pie(x=df2['total_amount'],labels=df2.index)
plt.show()
# index es el 'article_name' del df2
# 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'])
plt.xticks(rotation=60)
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']])
# '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'])
plt.show()
# RESOLUCIÓN
df_menosv=(my_df.groupby(by='article_name').sum()).sort_values('quantity', ascending=True).head(10)
df_menosv.drop(['week'], axis='columns', inplace=True)
print('ARTICULOS MENOS VENDIDOS')
print(df_menosv)
#RESOLUCION GRAFICA
plt.bar(df_menosv.index, df_menosv['quantity'], color='palevioletred' )
plt.xticks(rotation=90)
plt.title('ARTICULOS MENOS VENDIDOS')
plt.xlabel("Articulos")
plt.ylabel("Cantidad")
plt.show()
ARTICULOS MENOS VENDIDOS
quantity total_amount
article_name
Wi-Fi Card 141 $ 8,405.01
Keyboard 165 $ 3,729.00
Fan Cooler 205 $ 871.25
Case 206 $ 7,807.40
Chair 207 $ 69,477.48
Monitor 208 $ 47,840.00
Video Card 209 $ 27,483.50
Mesh Wi-Fi X 2 213 $ 6,922.50
Scanner 221 $ 40,885.00
Desk 223 $ 29,012.30
# RESOLUCIÓN
df_WiFiCard = my_df[my_df['article_name'] == 'Wi-Fi Card']
df_WiFiCard_sellers = (df_WiFiCard.groupby(by='seller_name').sum()).sort_values('quantity', ascending=False)
df_WiFiCard_sellers.drop(['week'], axis='columns', inplace=True)
print("VENDEDORES DEL ARTICULO WI-FI CARD")
print(df_WiFiCard_sellers.head())
#RESOLUCION GRAFICA
plt.bar(df_WiFiCard_sellers.index, df_WiFiCard_sellers['quantity'], color='palevioletred' )
plt.xticks(rotation=60)
plt.title('VENDEDORES DE "Wi-Fi card"')
plt.xlabel("Vendedores")
plt.ylabel("Cantidad")
plt.show()
VENDEDORES DEL ARTICULO WI-FI CARD
quantity total_amount
seller_name
Kati Innot 35 $ 2,086.35
Oliviero Charkham 21 $ 1,251.81
Aveline Swanwick 16 $ 953.76
Jase Doy 13 $ 774.93
Ewell Peres 12 $ 715.32
df_Seller1 = df_WiFiCard[df_WiFiCard['seller_name'] == 'Kati Innot']
df_Seller_Country = (df_Seller1.groupby(by='country_name').sum()).sort_values('quantity', ascending=False)
df_Seller_Country.drop(['week'], axis='columns', inplace=True)
print('Paises en los que Kati Innot, logró vender el articulo "Wi-Fi card"')
print(df_Seller_Country)
#RESOLUCION GRAFICA
e=(0.05,0.05,0.05)
a=['plum','mediumpurple', 'darkorchid', 'm', 'mediumvioletred', 'palevioletred']
plt.pie(df_Seller_Country['quantity'],labels=df_Seller_Country.index,autopct='%1.2f%%',explode=e, colors=a,pctdistance=0.65)
plt.show()
Paises en los que Kati Innot, logró vender el articulo "Wi-Fi card"
quantity total_amount
country_name
Peru 19 $ 1,132.59
Brazil 8 $ 476.88
Mexico 8 $ 476.88
df_CountryWiFicard = (df_WiFiCard.groupby(by='country_name').sum()).sort_values('quantity', ascending=False)
df_CountryWiFicard.drop(['week'], axis='columns', inplace=True)
print('PAISES EN LOS QUE SE COMERCIALIZA EL ARTICULO "WI-FI card"')
print(df_CountryWiFicard)
#RESOLUCIÓN GRAFICA
df_3Countries=df_CountryWiFicard
e=(0.25,0.25,0.25,0,0,0)
a=['mediumpurple', 'darkorchid','plum', 'm', 'mediumvioletred', 'palevioletred']
plt.pie(df_3Countries['quantity'],labels=df_3Countries.index,startangle=45,autopct='%1.2f%%', explode=e, colors=a,pctdistance=0.65)
plt.show()
PAISES EN LOS QUE SE COMERCIALIZA EL ARTICULO "WI-FI card"
quantity total_amount
country_name
Brazil 37 $ 2,205.57
Mexico 33 $ 1,967.13
Peru 27 $ 1,609.47
Colombia 25 $ 1,490.25
Argentina 12 $ 715.32
Honduras 7 $ 417.27