uniform_type=True)
area_attrs = ['user_live_province', 'user_live_city']
resource_dir = '../resources'
X_train = X_train_datapreprocessing.china_area_number_mapping(
area_attrs, resource_dir)
X_train = X_train_datapreprocessing.transform_dtype(area_attrs,
d_type=[int],
uniform_type=True)
X_train = X_train_datapreprocessing.dummies_and_fillna()
#X_train.info()
#print(X_train.head(5))
Gini_DF = pandas.concat([X_train, Y_train], axis=1)
#gini_attrs = Gini_DF.axes[1]
gini_attrs = list(Gini_DF.columns.values)
gini = GiniIndex(Gini_DF, gini_attrs, target_key, Gini_DF[target_key])
gini_index_dict = gini.gini_index()
gini_list = sorted(gini_index_dict.items(), key=lambda item: item[1])
for item in gini_list:
print(item)
scoring = 'accuracy'
models = []
models.append(('LR', LogisticRegression()))
models.append(('CART', DecisionTreeClassifier()))
#models.append(('LDA',LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('NB', GaussianNB()))
models.append(('RF', RandomForestClassifier()))
#models.append(('SVM',SVC()))
if __name__ == "__main__":
file_fullpath = '/home/login01/Workspaces/python/dataset/cs.csv'
#df = pandas.read_csv(file_fullpath,sep=',',index_col=0,na_values='NA',dtype=object,low_memory=False)
#df = pandas.read_csv(file_fullpath,sep=',',index_col=0,na_values='NA',low_memory=False)
df = pandas.read_csv(file_fullpath,
sep=',',
na_values='NA',
low_memory=False)
attribute = [
"RevolvingUtilizationOfUnsecuredLines", "age",
"NumberOfTime30-59DaysPastDueNotWorse", "DebtRatio", "MonthlyIncome",
"NumberOfOpenCreditLinesAndLoans", "NumberOfTimes90DaysLate",
"NumberRealEstateLoansOrLines", "NumberOfTime60-89DaysPastDueNotWorse",
"NumberOfDependents"
]
target_key = "SeriousDlqin2yrs"
df[target_key] = df[target_key].fillna(0)
target = df[target_key]
#pandas.set_option('display.max_rows', None)
#print(target)
gini = GiniIndex(df, attribute, target_key, target)
#mygini_index = gini.gini_index()
#print("mygini_score:", mygini_index)
mygini_index_dict = gini.gini_index()
gini_list = sorted(mygini_index_dict.items(), key=lambda item: item[1])
print("Gini index of each attribute:")
#for key,val in mygini_index_dict.items():
# print("%s:%s" % (key,val))
for item in gini_list:
print(item)