stop =N
else:
stop = start +len_fold
test = data.ix[rows[start:stop]]
train = data.ix[rows[:start]+rows[stop:]]
if resample:
train_len=start+N-stop
no_resamples = N-train_len
train_rows = list(train.index)
random_extra_rows =[random.choice(train_rows) for row in range(no_resamples)]
train_rows = train_rows+random_extra_rows
train=train.ix[train_rows]
yield {'test':test, 'train':train}
start=stop
df=ct.cleaneddf(no_bins=10)[0]
df2=ct.cleaneddf(no_bins=10)[1]
df=df[['Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch',
'Fare', 'Embarked']]
data_type_dict={'Survived':'nominal', 'Pclass':'ordinal', 'Sex':'nominal',
'Age':'ordinal', 'SibSp':'ordinal', 'Parch':'ordinal',
'Fare':'ordinal', 'Embarked':'nominal'}
def tree_train(data_type_dict, train_data,test_data, response, no_folds,
min_node_size, max_depth, no_iter):
parameters={'min_node_size':min_node_size, 'max_node_depth':max_depth,
'threshold':0, 'metric_kind':'Gini', 'alpha':0,
'response':response}
model=ticart.ClassificationTree()
else:
stop = start +len_fold
test = data.ix[rows[start:stop]]
train = data.ix[rows[:start]+rows[stop:]]
if resample:
train_len=start+N-stop
no_resamples = N-train_len
train_rows = list(train.index)
random_extra_rows =[random.choice(train_rows) for row in range(no_resamples)]
train_rows = train_rows+random_extra_rows
train=train.ix[train_rows]
yield {'test':test, 'train':train}
start=stop
df = ct.cleaneddf(no_bins=10)[0]
df2=ct.cleaneddf(no_bins=10)[1]
df=df[['Survived', 'Pclass', 'Sex', 'Age', 'SibSp', 'Parch',
'Fare', 'Embarked']]
data_type_dict={'Survived':'nominal', 'Pclass':'ordinal', 'Sex':'nominal',
'Age':'ordinal', 'SibSp':'ordinal', 'Parch':'ordinal',
'Fare':'ordinal', 'Embarked':'nominal'}
def tree_train(data_type_dict, train_data,test_data, response, no_folds,
min_node_size, max_depth, no_iter):
parameters={'min_node_size':min_node_size, 'max_node_depth':max_depth,
'threshold':0, 'metric_kind':'Gini', 'alpha':0,
'response':response}
model=ticart.ClassificationTree()
# -*- coding: utf-8 -*-
import pandas as pd
import numpy as np
import cleantitanic as ct
import matplotlib.pylab as plt
data = ct.cleaneddf()
traindf, testdf =data[0], data[1]
def proportionSurvived(discreteVar):
by_var = traindf.groupby([discreteVar,'Survived'])
table = by_var.size().unstack()
normedtable = table.div(table.sum(1), axis=0)
return normedtable
discreteVarList = ['Sex', 'Pclass', 'Embarked']
fig1, axes1 = plt.subplots(3,1)
for i in range(3):
var = discreteVarList[i]
table = proportionSurvived(var)
table.plot(kind='barh', stacked=True, ax=axes1[i])
fig1.show()
fig2, axes2 = plt.subplots(2,3)
genders=traindf.Sex.unique()
classes=traindf.Pclass.unique()
root_list = []
root_list.append(root_index)
layout = g.layout_reingold_tilford(root=root_list)
ig.plot(g, layout=layout, margin=margin)
def predict(self, data_point, class_probs=False):
if class_probs:
return self.vertices[0].get_data_leaf(data_point).prediction
else:
return self.vertices[0].get_data_leaf(data_point).predicted_class
# https://triangleinequality.wordpress.com/2013/09/01/decision-trees-part-3-pruning-your-tree/
if __name__ == '__main__':
import cleantitanic as ct
df = ct.cleaneddf()[0]
df = df[[
'survived', 'pclass', 'sex', 'age', 'sibsp', 'parch', 'fare',
'embarked'
]]
data_type_dict = {
'survived': 'nominal',
'pclass': 'ordinal',
'sex': 'nominal',
'age': 'ordinal',
'sibsp': 'ordinal',
'parch': 'ordinal',
'fare': 'ordinal',
'embarked': 'nominal'
}
g = ClassificationTree()
root_list = []
root_list.append(root_index)
layout = g.layout_reingold_tilford(root=root_list)
ig.plot(g, layout=layout, margin=margin)
def predict(self, data_point, class_probs=False): #预测函数
if class_probs:
return self.vertices[0].get_data_leaf(data_point).prediction
else:
return self.vertices[0].get_data_leaf(data_point).predicted_class
# https://triangleinequality.wordpress.com/2013/09/01/decision-trees-part-3-pruning-your-tree/
if __name__ == '__main__':
import cleantitanic as ct
df = ct.cleaneddf()[0] #这个是在进行数据的预处理
df = df[[
'survived', 'pclass', 'sex', 'age', 'sibsp', 'parch', 'fare',
'embarked'
]] #select relevant datas
data_type_dict = {
'survived': 'nominal',
'pclass': 'ordinal',
'sex': 'nominal', #离散特征
'age': 'ordinal', #连续特征
'sibsp': 'ordinal',
'parch': 'ordinal',
'fare': 'ordinal',
'embarked': 'nominal'
}
g = ClassificationTree()
else:
if type(self.pivot) ==set:
if datapoint[self.split_attribute] in self.pivot:
return self.left
else:
return self.right
else:
if datapoint[self.split_attribute] <=self.pivot:
return self.left
else:
return self.right
#Test Code Here
t=PivotDecisionTree()
t.create_vertex()
t.set_root(t.vertices[0])
root = t.get_root()
t.leaves.add(root)
t.split_vertex(vertex=t.get_root(), split_attribute='sex', pivot=set(['female']))
import cleantitanic as ct
data = ct.cleaneddf()[0]
t.response='survived'
root = t.get_root()
root.local_data=root.local_filter(data)
for child in root.children:
child.local_data=child.local_filter(root.local_data)
t.set_predictions()
for leaf in t.leaves:
print leaf.prediction
