Pythonデータマイニングの入門と実践1:コンピューティングサポートと信頼性
import numpy as np
from collections import defaultdict
#First,how many rows contain our premise:that a person is buying apples
'''num_apple_purchases=0
for sample in X:
if sample[3]==1: #this person bought apples
num_apple_purchases+=1
print num_apple_purchases'''
def calS(X,n_features):
#print n_features
#print X[:5]#every row is a purchase record,evey column is a product
#five kinds of product
#bread,milk,cheese,apple and banana
valid_rules=defaultdict(int)
invalid_rules=defaultdict(int)
num_occurances=defaultdict(int)
print X
for sample in X:
for premise in range(5):
if sample[premise]==0:continue
num_occurances[premise]+=1
for conclusion in range(n_features):
if premise==conclusion:continue
if sample[conclusion]==1:
valid_rules[(premise,conclusion)] += 1
else:
invalid_rules[(premise,conclusion)] += 1
support=valid_rules
confidence=defaultdict(float)
for premise,conclusion in valid_rules.keys():
rule=(premise,conclusion)
confidence[rule]=float(valid_rules[rule])/num_occurances[premise]#ここでvalid_rulesのルールエントリ数intからfloatに変換
return support,confidence
def print_rule(premise,conclusion,support,confidence,features):
premise_name=features[premise]
conclusion_name=features[conclusion]
print("Rule:If a person buys {0} they will also buy {1}".format(premise_name,conclusion_name))
print("-Support:{0}".format(support[(premise,conclusion)]))
print("-Confidence:{0:.3f}".format(confidence[(premise,conclusion)]))
if __name__ == '__main__':
X=np.loadtxt("affinity_dataset.txt")
n_samples,n_features=X.shape
premise=1
conclusion=3
support,confidence=calS(X,n_features)
features = ["bread", "milk", "cheese", "apples", "bananas"]
print support,confidence
print_rule(premise,conclusion,support,confidence,features)
from collections import defaultdict
#First,how many rows contain our premise:that a person is buying apples
'''num_apple_purchases=0
for sample in X:
if sample[3]==1: #this person bought apples
num_apple_purchases+=1
print num_apple_purchases'''
def calS(X,n_features):
#print n_features
#print X[:5]#every row is a purchase record,evey column is a product
#five kinds of product
#bread,milk,cheese,apple and banana
valid_rules=defaultdict(int)
invalid_rules=defaultdict(int)
num_occurances=defaultdict(int)
print X
for sample in X:
for premise in range(5):
if sample[premise]==0:continue
num_occurances[premise]+=1
for conclusion in range(n_features):
if premise==conclusion:continue
if sample[conclusion]==1:
valid_rules[(premise,conclusion)] += 1
else:
invalid_rules[(premise,conclusion)] += 1
support=valid_rules
confidence=defaultdict(float)
for premise,conclusion in valid_rules.keys():
rule=(premise,conclusion)
confidence[rule]=float(valid_rules[rule])/num_occurances[premise]#ここでvalid_rulesのルールエントリ数intからfloatに変換
return support,confidence
def print_rule(premise,conclusion,support,confidence,features):
premise_name=features[premise]
conclusion_name=features[conclusion]
print("Rule:If a person buys {0} they will also buy {1}".format(premise_name,conclusion_name))
print("-Support:{0}".format(support[(premise,conclusion)]))
print("-Confidence:{0:.3f}".format(confidence[(premise,conclusion)]))
if __name__ == '__main__':
X=np.loadtxt("affinity_dataset.txt")
n_samples,n_features=X.shape
premise=1
conclusion=3
support,confidence=calS(X,n_features)
features = ["bread", "milk", "cheese", "apples", "bananas"]
print support,confidence
print_rule(premise,conclusion,support,confidence,features)