I am working with the titanic dataset and using decision trees for analyzing the age covariate. I'd like just to see whether kids are more likely to survive than adults. I implemented my own Gini coefficient and I had plot the coefficient by age: dataset here titanic ds
import pandas as pd
import seaborn
import matplotlib.pyplot as plt
from sklearn import tree
import graphviz
import numpy as np
def gini_by_age(df, t):
df['age_group'] = df['age'].apply(lambda row : 0 if row <= t else 1)
kids = df[df['age_group'] == 0]
kids0 = kids[kids['survived'] == 0]
kids1 = kids[kids['survived'] == 1]
adults = df[df['age_group'] == 1]
adults0 = adults[adults['survived'] == 0]
adults1 = adults[adults['survived'] == 1]
gk = 1 - (len(kids0)**2 + len(kids1)**2)/float(len(kids))**2
ga = 1 - (len(adults0)**2 + len(adults1)**2)/float(len(adults))**2
return gk + ga
def plot_gini_by_age(df):
ages = range(2,25)
y = [gini_by_age(df, a) for a in ages]
plt.plot(ages, y)
plt.show()
def use_tree(df):
X = np.array(df['age']).reshape((len(df['age']),1))
y = df['survived']
clf = tree.DecisionTreeClassifier(max_depth=1).fit(X,y)
dot_data = tree.export_graphviz(clf, out_file=None)
graph = graphviz.Source(dot_data)
graph.render("age")
titanic_df = pd.read_csv("titanic_ds.csv")
ages_cov = titanic_df[['age', 'survived']].dropna()
plot_gini_by_age(ages_cov)
use_tree(ages_cov)
print gini_by_age(ages_cov, 5)
print gini_by_age(ages_cov, 8.5)
print gini_by_age(ages_cov, 15)
output: 0.925844132419 0.937732003001 0.963875889772 I see from the plot that gini coefficient has local minima at roughly 5, 8 and 15 years old and the best is at 5. But scikit gives me 8.5 years old as the best split. What is wrong here?
graphviz
$\endgroup$