TP Final Integrador

# A veces necesitamos instalar nuevas librerías en nuestros proyectos !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 8.9 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 22.1.2 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 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"]) print(df_articles)

    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
5        20020             Chair     335.64
6        20021             Modem      67.50
7        20022    Range Extender      20.45
8        20023          Notebook    1000.00
9        20024           Netbook     145.00
10       20025               HDD      54.62
11       20026               SDD      22.00
12       20027        Ram Memory      35.95
13       20028       Motherboard     138.38
14       20029             Mouse      30.30
15       20030        Fan Cooler       4.25
16       20031            Webcam      20.07
17       20032          Keyboard      22.60
18       20033        Headphones      23.30
19       20034           Scanner     185.00
20       20035              Case      37.90
21       20036        Video Card     131.50
22       20037               CPU     139.62
23       20038      Power Supply      43.95
24       20039     Water Cooling      67.50
25       20040          Heatsink      10.00
26       20041         Usb Cable       2.95
27       20042        Sata Cable       2.14
28       20043  Pci Express Port      10.12
29       20044        Wi-Fi Card      59.61
30       20045    Mesh Wi-Fi X 2      32.50

#Vendedores df_sellers =pd.read_excel("/work/data/sellers.xlsx",index_col=0) print(df_sellers)

                 seller_name
seller_id                   
1           Aveline Swanwick
2                   Jase Doy
3          Oliviero Charkham
4           Cornie Wynrehame
5                Ewell Peres
6           Milly Christoffe
7                 Kati Innot
8              Tobin Roselli
9               Onida Cosely
10           Cirilo Grandham
11           Vasily Danilyuk
12          Brockie Patience
13           Arnold Kilkenny
14            Janel O'Curran
15           Daisie Slograve

#Órdenes df_orders=pd.read_csv("/work/data/orders.csv") print(df_orders)

     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
..        ...   ...         ...       ...        ...          ...
995     16019     4       20021         1          7       Brazil
996     16020     4       20040        15         15       Brazil
997     16021     4       20040         2         11     Colombia
998     16022     4       20018        14         11       Brazil
999     16023     4       20026        12          9       Brazil

[1000 rows x 6 columns]

# Exploración del df de artículos print("Muestra de datos") print(df_articles.head()) print("\nFormato del dataframe") print(df_articles.shape) print("\nBúqueda de valores nulos") print(df_articles.isnull().sum()) print("\nFormato de los datos") 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)

Búqueda de valores nulos
article_id      0
article_name    0
unit_price      0
dtype: int64

Formato de los datos
article_id       int64
article_name    object
unit_price      object
dtype: object

# Exploración del df de vendedores print("Muestra de datos") print(df_sellers.head()) print("\nFormato del dataframe") print(df_sellers.shape) print("\nBúqueda de valores nulos") print(df_sellers.isnull().sum()) print("\nFormato de los datos") 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)

Búqueda de valores nulos
seller_name    0
dtype: int64

Formato de los datos
seller_name    object
dtype: object

# Exploración del df de órdenes print("Muestra de datos") print(df_orders.head()) print("\nFormato del dataframe") print(df_orders.shape) print("\nBúqueda de valores nulos") print(df_orders.isnull().sum()) print("\nFormato de los datos") 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)

Búqueda de valores nulos
order_id        0
week            0
article_id      0
quantity        0
seller_id       0
country_name    0
dtype: int64

Formato de los datos
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

#Creo una copia del df_orders my_df=df_orders.copy() #Cambio el índice del df_articles df_articles.set_index("article_id", inplace=True) print(df_articles.loc[20017]["article_name"]) print(df_articles.head())

Monitor
           article_name  unit_price
article_id                         
20015        Smartphone      525.00
20016           Full Pc     2127.81
20017           Monitor      230.00
20018            Tablet      130.00
20019              Desk      130.10

print(my_df.head())

   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

#Agrego las columnas que me faltan 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(my_df.head())

   order_id  week  article_id  quantity  seller_id country_name  article_name  \
0     15024     1       20039        10         10         Peru         20039   
1     15025     1       20029        15          5         Peru         20029   
2     15026     1       20024         5         14      Bolivia         20024   
3     15027     1       20018         9         14       Brazil         20018   
4     15028     1       20035         6         15       Mexico         20035   

   total_amount  seller_name  
0         20039           10  
1         20029            5  
2         20024           14  
3         20018           14  
4         20035           15

#Reemplazar los datos en las nuevas columnas #Lista de los índices #print(my_df.index) #print(len(my_df.index)) for i in range(len(my_df.index)): #columna article_name #Cargo el nombre del artículo en una variable article=df_articles.loc[my_df.loc[i]["article_name"]]["article_name"] #se lo asigno a la columna y registro que corresponde my_df.loc[i,"article_name"]=article #columna total_amount my_df.loc[i,"total_amount"]=my_df.loc[i,"quantity"]*df_articles.loc[my_df.loc[i]["total_amount"]]["unit_price"] #columna de seller_name my_df.loc[i,"seller_name"]=df_sellers.loc[my_df.loc[i]["seller_name"]]["seller_name"] print(my_df.head())

   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   

    article_name  total_amount      seller_name  
0  Water Cooling         675.0  Cirilo Grandham  
1          Mouse         454.5      Ewell Peres  
2        Netbook         725.0   Janel O'Curran  
3         Tablet        1170.0   Janel O'Curran  
4           Case         227.4  Daisie Slograve

#Elimino las coumnas que no necesito my_df.drop(["order_id","article_id","seller_id"],axis="columns",inplace=True) print(my_df.head())

   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

#Método merge d1=pd.DataFrame({"mes":["ene","feb","mar","abr"],"ventas":[10,20,30,15]}) d2=pd.DataFrame({"mes":["ene","feb","mar","abr"],"costos":[7,16,25,12]}) print(pd.merge(d1,d2))

   mes  ventas  costos
0  ene      10       7
1  feb      20      16
2  mar      30      25
3  abr      15      12

# RESOLUCIÓN ANALÍTICA my_df2=my_df.groupby("article_name").sum() por_cant=my_df2.sort_values("quantity",ascending=False) print(por_cant["quantity"].head(1))

article_name
HDD    413
Name: quantity, dtype: int64

# RESOLUCIÓN GRÁFICA sns.displot(my_df, x="article_name") plt.xticks(rotation=90) plt.show

# RESOLUCIÓN ANALÍTICA my_df3=(my_df.groupby("article_name").sum()).sort_values("total_amount",ascending=False).head(5) print(my_df3["total_amount"])

article_name
Full Pc       538335.93
Notebook      251000.00
Smartphone    152250.00
Chair          69477.48
Tablet         48620.00
Name: total_amount, dtype: float64

# RESOLUCIÓN GRÁFICA plt.pie(x=my_df3["total_amount"],autopct="%1.2f%%",labels=my_df3.index) plt.show()

# RESOLUCIÓN ANALÍTICA df4=(my_df.groupby("seller_name").sum()).sort_values("total_amount",ascending=False) print(df4[["quantity"]+["total_amount"]])

                   quantity  total_amount
seller_name                              
Janel O'Curran          703     192832.47
Brockie Patience        441     142709.88
Oliviero Charkham       555     141329.76
Vasily Danilyuk         521     129157.55
Daisie Slograve         554     120520.11
Aveline Swanwick        629     118874.33
Arnold Kilkenny         583      94552.04
Kati Innot              512      83704.62
Jase Doy                582      80628.31
Ewell Peres             496      78144.32
Onida Cosely            535      77373.37
Milly Christoffe        442      61733.69
Tobin Roselli           519      56984.42
Cornie Wynrehame        523      52253.57
Cirilo Grandham         470      45009.40

# RESOLUCIÓN GRÁFICA plt.bar(df4.index,df4["total_amount"]) plt.xticks(rotation=60) plt.show()

# RESOLUCIÓN ANALÍTICA df5=(my_df.groupby("week").sum()).sort_values("total_amount",ascending=False) print(df5)

      quantity  total_amount
week                        
1         2449     507458.81
2         2444     415364.44
3         2114     329140.03
4         1058     223844.56

# RESOLUCIÓN GRÁFICA plt.bar(df5.index,df5["total_amount"]) plt.show()

# RESOLUCIÓN ANALÍTICA df6=(my_df.groupby("country_name").sum()).sort_values("total_amount",ascending=False).head(5) print(df6[["quantity"]+["total_amount"]])

              quantity  total_amount
country_name                        
Brazil            2515     441271.85
Argentina          947     205832.78
Colombia           881     177514.29
Peru              1027     161421.12
Mexico             846     138619.99

#RESOLUCION GRAFICA plt.barh(df6.index,df6["total_amount"]) plt.xticks(rotation=0) plt.show()

# RESOLUCIÓN ANALÍTICA 1 df7=(my_df.groupby("country_name").sum()).sort_values("total_amount",ascending=False).tail(6) print(df7[["quantity"]+["total_amount"]])

              quantity  total_amount
country_name                        
Chile              231      24660.98
Bolivia            181      22682.80
Uruguay             92      17843.09
Ecuador            129      17475.30
Paraguay           123       8195.12
Puerto Rico         12       1265.43

#RESOLUCION GRAFICA plt.barh(df7.index,df7["total_amount"]) plt.xticks(rotation=0) plt.show()

# RESOLUCIÓN ANALÍTICA 2 df8=(my_df.groupby("article_name").sum()).sort_values("total_amount",ascending=False).tail(6) print(df8[["quantity"]+["total_amount"]])

                  quantity  total_amount
article_name                            
Keyboard               165       3729.00
Pci Express Port       291       2944.92
Heatsink               280       2800.00
Fan Cooler             205        871.25
Usb Cable              273        805.35
Sata Cable             264        564.96

#RESOLUCION GRAFICA plt.barh(df8.index,df8["total_amount"]) plt.xticks(rotation=45) plt.show()

ff=my_df[((my_df["article_name"]=="Keyboard")|(my_df["article_name"]=="Pci Express Port")|(my_df["article_name"]=="Heatsink")|(my_df["article_name"]=="Fan Cooler")|(my_df["article_name"]=="Usb Cable")|(my_df["article_name"]=="Sata Cable"))&((my_df["country_name"]=="Brazil")|(my_df["country_name"]=="Argentina")|(my_df["country_name"]=="Colombia")|(my_df["country_name"]=="Peru")|(my_df["country_name"]=="Mexico"))] sns.barplot(x="country_name",y="total_amount",hue="week",data=ff)

sns.relplot(x="total_amount",y="country_name",col="week",data=ff)

bb=my_df[((my_df["article_name"]=="Keyboard")|(my_df["article_name"]=="Pci Express Port")|(my_df["article_name"]=="Heatsink")|(my_df["article_name"]=="Fan Cooler")|(my_df["article_name"]=="Usb Cable")|(my_df["article_name"]=="Sata Cable"))&((my_df["country_name"]=="Chile")|(my_df["country_name"]=="Bolivia")|(my_df["country_name"]=="Uruguay")|(my_df["country_name"]=="Ecuador")|(my_df["country_name"]=="Paraguay")|(my_df["country_name"]=="Puerto Rico"))] sns.barplot(x="country_name",y="total_amount",hue="week",data=bb)

sns.relplot(x="total_amount",y="country_name",col="week",data=bb)