De predictor insight-graphtabel voorbereiden

Introductie tot Predictive Analytics in Python

Nele Verbiest, Ph.D

Data Scientist @PythonPredictions

De predictor insight-graphtabel

disc_mean_gift	Incidentie	Omvang
[2, 78]	0.013042	20013
(78, 87]	0.029554	19997
(87, 94]	0.040831	20034
(94, 103]	0.063563	20405
(103, 197]	0.103524	19551

De predictor insight-graphtabel berekenen

# Laad de numpy-module
import numpy as np
# Functie die de predictor insight-graphtabel berekent
def create_pig_table(df, target, variable):

    # Groepeer op de variabele die je wilt plotten
    groups = df[[target,variable]].groupby(variable)

    # Bereken de omvang en incidentie van elke groep
    pig_table = groups[target].agg(Incidence = 'mean').reset_index()
    return pig_table

print(create_pig_table(basetable,"target","country")

country    Incidence    Size
India    0.050934    49849
UK    0.050512    10057
USA    0.048486    40094

Meerdere predictor insight-graphtabellen berekenen

variables = ["country", "gender", "disc_mean_gift", "age"]

# Lege dictionary.
pig_tables = {}

# Loop over alle variabelen
for variable in variables:

    # Maak de predictor insight-graphtabel
    pig_table = create_pig_table(basetable, "target", variable)

    # Sla de tabel op in de dictionary
    pig_tables[variable] = pig_table

print(create_pig_table(basetable,"target","country")

country    Incidence    Size
India    0.050934    49849
UK    0.050512    10057
USA    0.048486    40094

Laten we oefenen!

Introductie tot Predictive Analytics in Python