models.append(('AdaBoostClassifier', AdaBoostClassifier(random_state=45)))
models.append(
('ExtraTreesClassifier', ExtraTreesClassifier(random_state=seed)))
models.append(('GradientBoostingClassifier',
GradientBoostingClassifier(random_state=seed)))
rows = len(feature_list) * len(models)
result = pd.DataFrame(
columns=['model', 'features', 'train_score', 'test_score'])
# result = pd.DataFrame(
# np.zeros((rows, 4)),
# columns=['model', 'features', 'train_score', 'test_score'])
y = dataset.load('target', 'train')
clf = VotingClassifier(models)
for num_feature, cat_feature in feature_list:
print('{} + {}:'.format(num_feature, cat_feature), end='')
num_var = dataset.load(num_feature, 'train')
cat_var = dataset.load(cat_feature, 'train')
X = pd.concat([num_var, cat_var], axis=1)
cv_result = cross_validate(clf, X, y, cv=kfold)
train_score = cv_result['train_score'].mean()
test_score = cv_result['test_score'].mean()
print('train score:{:.4f}, test score:{:.4f}'.format(
'''
连续变量进行对数转换
'''
from util import dataset
from sklearn.preprocessing import MinMaxScaler
print('Loading data......')
train = dataset.load('numeric', 'train').astype(float)
test = dataset.load('numeric', 'test').astype(float)
num_col = dataset.load('numeric', 'feature')
scaler = MinMaxScaler()
for col in num_col:
scaler.fit(train[col].values.reshape(-1, 1))
train[col] = scaler.transform(train[col].values.reshape(-1, 1))
test[col] = scaler.transform(test[col].values.reshape(-1, 1))
print(train.head())
print('=' * 20)
print(test.head())
print('=' * 20)
print('Saving data......')
dataset(numeric_maxmin=train).save('train')
dataset(numeric_maxmin=test).save('test')
print('Done!')
'''
分类变量创建虚拟变量
'''
from util import dataset
import pandas as pd
print('Loading data......')
train = dataset.load('categorical', 'train')
test = dataset.load('categorical', 'test')
cat_col = dataset.load('categorical', 'feature')
for col in cat_col:
dummies = pd.get_dummies(train[col], prefix=col)
train = pd.concat([train, dummies], axis=1)
train.drop([col], axis=1, inplace=True)
dummies = pd.get_dummies(test[col], prefix=col)
test = pd.concat([test, dummies], axis=1)
test.drop([col], axis=1, inplace=True)
print('Saving data......')
dataset(categorical_dummy=train).save('train')
dataset(categorical_dummy=test).save('test')
print('Done!')
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.feature_selection import RFE
from sklearn.model_selection import cross_validate
from sklearn.model_selection import train_test_split
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve
from matplotlib import pyplot as plt
print('Loading Data...')
y = dataset.load('target', 'train')
X = dataset.load('new_feature', 'train')
# X.drop(['source'], axis=1, inplace=True)
# num_var = dataset.load('numeric_maxmin', 'train')
# cat_var = dataset.load('categorical_dummy', 'train')
# X = pd.concat([num_var, cat_var], axis=1)
# X_train, X_test, y_train, y_test = train_test_split(
# X, y, test_size=0.3, random_state=45)
lr = LogisticRegression(random_state=45)
kfold = StratifiedKFold(n_splits=10, random_state=45)
roc_base = 0.5
base_n = 1
'''
分类变量创建虚拟变量
'''
from util import dataset
import pandas as pd
from numericprocess import NumProcess
print('Loading data......')
cat_var = dataset.load('categorical', 'feature')
num_var = dataset.load('numeric', 'feature')
train = pd.concat(
[dataset.load('numeric', 'train'),
dataset.load('categorical', 'train')],
axis=1)
test = pd.concat(
[dataset.load('numeric', 'test'),
dataset.load('categorical', 'test')],
axis=1)
train['source'] = 'train'
test['source'] = 'test'
df = pd.concat([train, test], axis=0)
for x in range(len(cat_var)):
for y in range(len(cat_var)):
if x < y:
name = '{}&{}'.format(cat_var[x], cat_var[y])
df[name] = df[cat_var[x]].astype(str) + '&' + df[
import util.cluster as cluster
import matplotlib.pyplot as plt
from index.external import *
import csv
import sys
import numpy as np
from sklearn.cluster import KMeans
from sklearn.cluster import AgglomerativeClustering
import util.dataset as dataset
def argmax(scores):
return max(enumerate(scores), key=lambda x: x[1])[0] + 1
X, classes = dataset.load(sys.argv[1])
print 'Samples count: ', len(X), ', class count', len(set(classes))
max_cluster_count = int(sys.argv[2])
clusterizer_type = sys.argv[3]
rand_scores = []
jaccard_scores = []
fm_scores = []
f1_scores = []
file = open('res.txt', 'w')
for i in range(1, max_cluster_count + 1):
#print '----------', i, '----------'
clusterizer = None
if clusterizer_type == 'kmeans':
clusterizer = KMeans(n_clusters=i).fit(np.array(X))
elif clusterizer_type == 'ward':
import numpy as np
from util import dataset
data = dataset.load('custom_label', 'train')
print(data)
'''
删除变量
'''
from util import dataset
import pandas as pd
import numpy as np
# 分类变量
cat_col = dataset.load('categorical', 'feature')
num_col = dataset.load('numeric', 'feature')
ord_col = dataset.load('order', 'feature')
# 加载数据
print('LOADING......')
train = dataset.load('train', 'all')
test = dataset.load('test', 'all')
y = dataset.load('target', 'train')
train.drop([
'TotalWorkingYears', 'YearsAtCompany', 'YearsInCurrentRole',
'YearsWithCurrManager', 'JobRole', 'StockOptionLevel', 'Gender',
'DistanceFromHome', 'Education', 'PerformanceRating',
'RelationshipSatisfaction', 'TrainingTimesLastYear'
], axis=1, inplace=True)
test.drop([
'TotalWorkingYears', 'YearsAtCompany', 'YearsInCurrentRole',
'YearsWithCurrManager', 'JobRole', 'StockOptionLevel', 'Gender',
'DistanceFromHome', 'Education', 'PerformanceRating',
'RelationshipSatisfaction', 'TrainingTimesLastYear'
], axis=1, inplace=True)
'''
from util import dataset
import pandas as pd
import numpy as np
import chimerge
def meger(x, inver_list):
for i in range(len(inver_list)):
if x <= inver_list[i]:
return i + 1
return i + 2
print('Loading data......')
train = dataset.load('numeric', 'train')
test = dataset.load('numeric', 'test')
num_col = dataset.load('numeric', 'feature')
target = dataset.load('target', 'train')
df = pd.concat([train, target], axis=1)
for col in num_col:
_, interval_list = chimerge.ChiMerge(df, col, 'Attrition')
train[col] = train[col].map(lambda x: meger(x, interval_list))
test[col] = test[col].map(lambda x: meger(x, interval_list))
print(train.head())
print('=' * 20)
print(test.head())
ExtraTreesClassifier(random_state=seed, n_estimators=20)))
models.append(('GradientBoostingClassifier',
GradientBoostingClassifier(random_state=seed,
n_estimators=100,
max_depth=3)))
rows = len(feature_list) * len(models)
result = pd.DataFrame(
columns=['model', 'features', 'train_score', 'test_score'])
# result = pd.DataFrame(
# np.zeros((rows, 4)),
# columns=['model', 'features', 'train_score', 'test_score'])
y = dataset.load('target', 'train')
for num_feature, cat_feature in feature_list:
print('{} + {}:'.format(num_feature, cat_feature))
num_var = dataset.load(num_feature, 'train')
cat_var = dataset.load(cat_feature, 'train')
X = pd.concat([num_var, cat_var], axis=1)
test_num = dataset.load(num_feature, 'test')
test_cat = dataset.load(cat_feature, 'test')
X_test = pd.concat([test_num, test_cat], axis=1)
for name, clf in models:
print(name + ':', end='')
cv_result = cross_validate(estimator=clf, X=X, y=y, cv=kfold)
