TP Final Integrador 22612 - Lautaro Iriazabal

# A veces necesitamos instalar nuevas librerías en nuestros proyectos !pip install openpyxl==3.0.10

# 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)

# 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)

# 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)

df_articles['unit_price'] = df_articles['unit_price'].astype(float) print(df_articles.dtypes)

# 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)

# 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]]

# 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']])

# 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())

# 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))

# 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']])

# RESOLUCIÓN GRÁFICA plt.bar(df5.index, df5['total_amount']) plt.show() # 'week' es el index

# RESOLUCIÓN ANALITICA my_df5 = (my_df.groupby(by='country_name').sum()).sort_values('total_amount',ascending=False).head(7) print(my_df5['total_amount'])

# RESOLUCIÓN GRAFICA sns.barplot(y=my_df5['total_amount'], x=my_df5.index, palette='flare') plt.suptitle('TOP 10 Paises Mayores Compras Totales',fontsize='x-large') for pos in ['right', 'top', 'bottom', 'left']: plt.gca().spines[pos].set_visible(False) ingresos = my_df5['total_amount'].values for i, ingreso in enumerate(ingresos): v = '$ ' + str(int(ingreso)) plt.text(s=v, x=i, y=my_df5['total_amount'][i] + 15000, ha='center') plt.xlabel('') plt.yticks([]) plt.ylabel(ylabel='') plt.show()

# RESOLUCIÓN ANÁLITICA # Obtener Monto total desglosado por Pais df_pais_articulo = my_df.groupby(['country_name', 'article_name']).sum() # Obtener la lista de paises paises = my_df.groupby('country_name').sum().index.values # Seteo la estructura del DF my_df6 = pd.DataFrame(columns=['ARTICULO', 'MONTO'], index=paises) # Calcular los articulos mas vendidos por pais y guardarlas en df for p in paises: df = df_pais_articulo.loc[p] v = df.max()['total_amount'] a = df[(df['total_amount'] == v)].index[0] my_df6.loc[p] = {'ARTICULO': a, 'MONTO': v} my_df6 = my_df6.sort_values(['ARTICULO', 'MONTO']) my_df6.reset_index(inplace=True, drop=False) my_df6.columns = ['PAIS','ARTICULO', 'MONTO'] print(my_df6)

# RESOLUCIÓN GRÁFICA c = sns.color_palette('rocket', n_colors=my_df6.nunique(0)[1]) df_pivot = pd.pivot_table(my_df6, index='PAIS', columns='ARTICULO', values='MONTO', aggfunc='sum') df_pivot = df_pivot.sort_values(['CPU','Full Pc', 'Monitor', 'Notebook','Smartphone'], ascending=False) df_pivot.plot.barh(stacked=True, color=c, width=0.8) plt.suptitle(t='PRODUCTO QUE MAS SE VENDE EN CADA PAIS Y SU MONTO TOTAL', y=1.4, fontsize='x-large') for pos in ['right', 'top', 'bottom', 'left']: plt.gca().spines[pos].set_visible(False) ingresos = my_df6.values for ingreso in ingresos: v = '$ ' + str(int(ingreso[2])) i = df_pivot.index.values plt.text(s=v, x=ingreso[2] + 1000, y=np.where(i==ingreso[0])[0][0], va='center') plt.xlabel('') plt.xticks([]) plt.ylabel(ylabel='') plt.show()

# RESOLUCIÓN ANÁLITICA #Filtro del País que quiero analizar, Brasil filter_brasil=my_df['country_name']=='Brazil' brasil_df = my_df[filter_brasil] #Busco los articulos más vendidos correspondientes al país en cuestión brasil_agrupado_df=brasil_df.groupby("article_name").sum().sort_values('total_amount',ascending=False).drop(['week'], axis=1).head(10) print (brasil_agrupado_df)

# RESOLUCIÓN GRÁFICA colors = sns.color_palette('Set3')[0:9] plt.pie(brasil_agrupado_df['total_amount'], labels = brasil_agrupado_df.index, colors = colors, autopct='%.0f%%') plt.title('Desglose de Ventas Totales en el Brasil') plt.show()

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()

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()