def get_rules(encoded_transaction, min_support=0.07, min_threshold=1):
# 挖掘频繁项集
frequent_itemsets = apriori(encoded_transaction,
min_support=min_support,
use_colnames=True)
rules = ar(frequent_itemsets, metric='lift', min_threshold=min_threshold)
frequent_itemsets = frequent_itemsets.sort_values(by='support',
ascending=False)
print('频繁项集：', frequent_itemsets)
pd.options.display.max_columns = 100
rules = rules.sort_values(by='lift', ascending=False)
print('关联规则：', rules)
return frequent_itemsets, rules
def data_load(file):
try:
df = pd.read_csv(file, sep=';', encoding = 'utf-8', index_col=False,
error_bad_lines = False)
except:
print('incorrect file path')
return df
df = data_load(file)
df.head()
df.dtypes
df = df.loc[:,df.columns != 'id']
freq_items = ap(df,
min_support = 0.11,
use_colnames=True)
freq_items.head()
rules = ar(freq_items,
metric = 'lift',
min_threshold = 1)
rules.head()
rules['confidence'].sort_values(ascending = False).head(100)
rules['lift'].sort_values(ascending = False).head(100)
pd.set_option('display.max_columns', None)
rules[ (rules['lift'] >= 1) & (rules['confidence'] >= 0.8)]
for i in range(len(cgm)):
CGmax.append(maximum(cgm.loc[i]))
BOLmax.append(maximum(bol.loc[i]))
CG0.append(cgm.loc[i][5])
apriDF.append([
CalculateBins(max(cgm.loc[i])),
CalculateBins(cgm.loc[i][5]),
max(bol.loc[i])
])
#Apriori Algorithm
#For Most Frequent Itemsets
transEnc = TransactionEncoder()
transactions = pd.DataFrame(transEnc.fit(apriDF).transform(apriDF),
columns=transEnc.columns_)
rules = ar(ap(transactions, min_support=0.00000000001, use_colnames=True),
min_threshold=0.0)
rules["antecedent_len"] = rules["antecedents"].apply(lambda x: len(x))
for column in ['antecedents', 'consequents']:
rules[column] = rules[column].astype(str)
rules[column] = rules[column].str.replace(re.escape('frozenset({'), '')
rules[column] = rules[column].str.replace(re.escape('})'), '')
rules["SET"] = rules["antecedents"] + ',' + rules['consequents']
rules['SET'] = rules['SET'].str.replace("'", "")
rules['SET'] = rules.SET.apply(lambda x: x.split(','))
#rules.to_csv("Rules.csv")
li = rules['SET'].tolist()
y = [[(float(j)) for j in i] for i in li]
for i in y:
i.sort(reverse=True)
b = list()
for sublist in y:
from mlxtend.frequent_patterns import association_rules as ar
def deal(data):
return data.dropna().tolist()
df_arr = df.apply(deal, axis=1).tolist() # 转化成列表
te = TE() # 定义模型
df_tf = te.fit_transform(df_arr)
df = pd.DataFrame(df_tf, columns=te.columns_)
df
freq_itemsets = apriori(df, min_support=0.005, use_colnames=True)
freq_itemsets.sort_values(by='support', ascending=False, inplace=True)
freq_itemsets
a_r = ar(freq_itemsets, metric='lift')
a_r = a_r.sort_values(by='lift', ascending=False).reset_index(drop=True)
a_r
t = []
for i in range(a_r.shape[0]):
item = a_r.iloc[i]
t.append(
item.support /
math.sqrt(item['antecedent support'] * item['consequent support']))
a_r['cosine'] = t
t = []
for i in range(a_r.shape[0]):
item = a_r.iloc[i]
t.append(0.5 * (item.support / item['antecedent support'] +
item.support / item['consequent support']))
a_r['Kulc'] = t
##
## Defining the apriori algorithm.
##
freq_items = ap(encode_df,
min_support=0.0085,
use_colnames=True,
verbose=1,
low_memory=False)
print(freq_items.head())
##
## Defining the association rules algorithms to match and find similar items together based on confidence.
##
assocn_rules_conf = ar(freq_items, metric="confidence", min_threshold=0.25)
print(assocn_rules_conf)
##
## Defining the association rules algorithms to match and find similar items together based on support.
##
assocn_rules_supp = ar(freq_items, metric="support", min_threshold=0.005)
print(assocn_rules_supp)
##
##
## Plotting the scatter plot of Confidence Vs Support
##
plt.scatter(assocn_rules_conf['support'],
assocn_rules_conf['confidence'],