FilesExpand file tree

main

/

models.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

159 lines (146 loc) · 4.09 KB

main

/

models.py

Copy path

Top

File metadata and controls

• Code
• Blame

159 lines (146 loc) · 4.09 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

36

37

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

81

82

83

84

85

86

87

88

89

90

91

92

93

94

95

96

97

98

99

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

import os

import gc

import time

import json

import pickle

import numpy as np

import pandas as pd

import seaborn as sb

import xgboost as xgb

import lightgbm as lgb

import cloudpickle as cp

import matplotlib.pyplot as plt

import warnings

warnings.filterwarnings('ignore')

import torch

import torch.nn as nn

import torch.optim as optim

import torch.nn.functional as F

from torchsummary import summary

from torch.utils.data import DataLoader, Dataset

from tqdm.auto import tqdm

from scipy import stats

from numerapi import NumerAPI

from scipy.stats import pearsonr

from xgboost import XGBClassifier

from catboost import CatBoostClassifier

from sklearn.tree import *

from sklearn.metrics import *

from sklearn.ensemble import *

from sklearn.linear_model import *

from sklearn.decomposition import *

from sklearn.preprocessing import *

from sklearn.neural_network import *

from sklearn.model_selection import *

from sklearn.cluster._kmeans import KMeans

from sklearn.naive_bayes import GaussianNB

from sklearn.neighbors import LocalOutlierFactor

from sklearn.neighbors import KNeighborsClassifier

from imblearn.under_sampling import RandomUnderSampler

from sklearn.utils.class_weight import compute_class_weight

from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

def get_xgboost():

xgboost = xgb.XGBClassifier(

objective='multi:softprob',

num_class=5,

n_estimators=1000,

max_depth=10,

learning_rate=0.01,

random_state=42,

subsample=0.8,

colsample_bytree=0.8,

gamma=2,

min_child_weight=5,

reg_alpha=0.1,

reg_lambda=1.0,

eval_metric='mlogloss',

use_label_encoder=False

)

return xgboost

def get_random_forest():

random_forest = RandomForestClassifier(

n_estimators=1000,

max_depth=10,

min_samples_split=5,

min_samples_leaf=4,

max_features='sqrt',

bootstrap=True,

class_weight='balanced',

n_jobs=-1,

random_state=42,

max_samples=0.9,

oob_score=True,

criterion='gini',

verbose=1

)

return random_forest

def get_adaboost():

base_estimator = DecisionTreeClassifier(

class_weight='balanced',

max_features='sqrt',

max_depth=3,

random_state=42

)

adaboost = AdaBoostClassifier(

estimator=base_estimator,

n_estimators=1000,

learning_rate=0.01,

algorithm='SAMME.R',

random_state=42

)

return adaboost

def get_logistic_regression():

logistic = LogisticRegression(

class_weight='balanced',

random_state=42,

solver='saga',

penalty='l2',

C=0.25,

tol=1e-4,

max_iter=500,

n_jobs=-1

)

return logistic

def get_catboost():

catboost = CatBoostClassifier(

auto_class_weights='Balanced',

random_state=42,

iterations=500,

learning_rate=0.1,

depth=5,

l2_leaf_reg=3,

eval_metric='MultiClass',

early_stopping_rounds=20,

verbose=100

)

return catboost

def get_histogram_gb():

histogram_gb = HistGradientBoostingClassifier(

class_weight='balanced',

random_state=42,

learning_rate=0.001,

max_iter=100,

max_depth=10,

min_samples_leaf=20,

max_leaf_nodes=40,

l2_regularization=1.0,

max_bins=255,

early_stopping=True,

validation_fraction=0.1,

n_iter_no_change=50,

scoring='roc_auc_ovr',

loss='log_loss',

verbose=1

)

return histogram_gb

def get_lightgbm():

lightGBM = lgb.LGBMRegressor(

objective='regression',

n_estimators=10000,

learning_rate=0.01,

max_depth=10,

num_leaves=2**10,

colsample_bytree=0.1,

random_state=42

)

return lightGBM