flcore/config.yaml at main · DataTools4Heart/flcore · GitHub

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
################################################################################

# Flcore configuration file

################################################################################


################################################################################
# Experiment parameters
################################################################################

##############  Dataset type to use
# Possible values: , kaggle_hf, mnist, dt4h_format
dataset: dt4h_format
#custom
#libsvm
#kaggle_hf

# ****** * * * * * * *  *  *   *    *    *  *  * * * * * * * *******************
# New variables
# ****** * * * * * * *  *  *   *    *    *  *  * * * * * * * *******************
metadata_file: metadata.json
data_file : 3362-2045-1944.parquet
# Options: IQR STD MIN_MAX
normalization_method : IQR

train_labels: ["encounters_encounterClass","encounters_admissionYear","vital_signs_systolicBp_value_last",
               "patient_demographics_gender","patient_demographics_age","vital_signs_weight_value_last",
               "vital_signs_height_value_first","lab_results_crpNonHs_value_avg","lab_results_tropIHs_value_min"]
target_label: ["conditions_stroke_any"] #,"conditions_vd_any"]

train_size: 0.7
# ****** * * * * * * *  *  *   *    *    *  *  * * * * * * * *******************

##############  Number of clients (data centers) to use for training
num_clients: 1

############## Model type
# Possible values: logistic_regression, lsvc, elastic_net, random_forest, weighted_random_forest, xgb
# See README.md for a full list of supported models
model: random_forest
#logistic_regression
#random_forest

############## Training length
num_rounds: 50

############## Metric to select the best model
# Possible values: accuracy, balanced_accuracy, f1, precision, recall
checkpoint_selection_metric:  precision
#balanced_accuracy

############## Experiment logging
experiment:
  name: experiment_1
  log_path: logs
  debug: true


################################################################################
# Aggregation methods
################################################################################

############## Centre-dropout
# Possible values: None, random_dropout, Fast_at_odd_rounds, LessParticipants
dropout_method: None
dropout:
  percentage_drop: 50

############## Weight smoothing
# Possible values: None, SlowerQuartile, EqualVoting
smooth_method: None
smoothWeights:
  smoothing_strenght: 0.5

################################################################################
# Model specific parameters
################################################################################

# Number of features to select for model input

# info: If None, all features are used
# higher value of features may increase performance at the risk of overfitting
# Kaggle dataset has 9 features
# UKBB dataset has 40 features

linear_models:
  n_features: 9

# Random Forest
random_forest:
  balanced_rf: true

# Weighted Random Forest
weighted_random_forest:
  balanced_rf: true
  levelOfDetail: DecisionTree

# XGBoost
xgb:
  batch_size: 32
  num_iterations: 100
  task_type: BINARY
  tree_num: 500


held_out_center_id: -1

################################################################################
# Library configuration

seed: 42

local_port: 8081

data_path: dataset/icrc-dataset/

production_mode: False # Turn on to use environment variables such as data path, server address, certificates etc.