TP Final Integrador 22612

# 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

Peru

Bolivia

Brazil

Mexico

# RESOLUCIÓN ANALÍTICA # df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False) # print(df7.head()) # print(df7[['quantity']].head()) # print() # df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False).reset_index() # print(df7.head()) # df7_2 = df7[['article_name', 'quantity']].groupby('article_name').sum('quantity').sort_values('quantity', ascending=False) # print(df7_2.head()) # print() # print(df7_2.head().index) # print(df7_2.head().index[0]) # df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False).head() # df7 = my_df.groupby(by='article_name')[['quantity'] + ['total_amount']].sum().sort_values('quantity',ascending=False).head() # print(df7) # print(df7.head().index) # df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False) # print(df7.iloc[0:5]) # df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False).reset_index() # print(df7.iloc[0:5]) # df7 = my_df.groupby(by='article_name')['quantity'].sum().sort_values(ascending=False) # df7 = my_df.groupby(by='article_name').sum().sort_values('quantity',ascending=False) # print(df7) # print(df7.loc['HDD':'Netbook']) # print(df7.loc['HDD':'Netbook']['quantity']) # df7 = my_df.groupby(by='article_name').agg({'quantity':'sum'}).sort_values('quantity', ascending=False) # print(df7.head()) # df7 = my_df.groupby(by='article_name').agg({'quantity':'sum'}).sort_values('quantity', ascending=False).rename(columns={'quantity':'Cantidad'}).sort_values('Cantidad', ascending=False) # print(df7.head()) # df7 = my_df.groupby(by='article_name').agg({'quantity':'sum'}).sort_values('quantity', ascending=False).reset_index().rename(columns={'quantity':'Cantidad'}).sort_values('Cantidad', ascending=False) # print(df7.head()) # df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False).head() df7 = my_df.groupby(by='article_name').sum().sort_values('quantity', ascending=False) pd.options.display.float_format= '$ {:,.2f}'.format # print(df7[['quantity']].head()) print(df7[['quantity','total_amount']].head()) # print(df7[['quantity','total_amount']])

              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.reset_index().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

# RESOLUCIÓN GRÁFICA plt.pie(x=df2['total_amount'], labels=df2.index, autopct='%1.2f%%') 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.bar(df4.index, df4['total_amount']) plt.xticks(rotation=90) 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.bar(df5.index, df5['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 #RESOLUCIÓN ANALÍTICA df5 = my_df.groupby(['country_name','article_name'])[['quantity','total_amount']] print('Producto más vendido de Argentina') print(df5.loc['Argentina'].head(1)[['quantity']]) print() print('Producto màs vendido de Brasil') print(df5-loc['Brasil'].head(1)[['quantity']]) #RESOLUCIÒN GRÁFICA

Execution error

NameError: name 'my_df' is not defined

# RESOLUCIÓN # Evolución de Ventas por producto. # Tomar 2 países y 'week' como variable categórica # Resolución Analítica y Gráfica

# RESOLUCIÓN # Mejor vendedor/producto. Mostrar importe/cantidad. Comparar 2 países (variable categórica) # Resolución Analítica y Gráfica

df6 = my_df[my_df['country_name'] == 'Brazil'] #A partir del anterior, ordenar vendedores por total de ventas vendedores_pais = df6.groupby('seller_name').sum().sort_values('total_amount', ascending=False) vendedores_pais.head() #La mejor vendedora daisie slograve

weekint64

quantityint64

Daisie Slograve

226

Aveline Swanwick

227

Arnold Kilkenny

184

Kati Innot

151

Tobin Roselli

211

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