keystroke-scripts/config_debug.json at master · FakeProfileDetection/keystroke-scripts · 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
{
  "dataset_path": "../eda/ml-experients-without-outliers2025-05-31_143027/imputation_user/dataset_1_full_without_outliers_IL_filtered.csv",
  "early_stopping": false,
  "seeds": [42, 12345],
  "output_affix": "debug",
  "show_class_distributions": false,
  "draw_feature_importance": true,
  "debug": true,
  "use_gpu": false,
  "metadata": {
    "raw_data": "loadable_Combined_HU_HT",
    "processed_data": "processed_data-2025-05-31_140105-UbuntuSungoddess",
    "extracted_features_dir": "ml-experients-without-outliers2025-05-31_143027",
    "description": "Full dataset without outliers, filtered for IL users",
    "version": "1.0",
    "note": "This may need to be updated after running the experiment."
  },

    "models_to_train": [
    "RandomForest",
    "XGBoost",
    "CatBoost",
    "SVM",
    "MLP"
  ],

  "experiments": [
    {"name": "T_vs_F", "platform": true, "train": [3], "test": 1},
    {"name": "T_vs_I", "platform": true, "train": [3], "test": 2}

  ],

  "param_grids": {
    "randomforest": {
      "n_estimators": [50],
      "max_depth": [10]
    },

    "xgboost": {
      "n_estimators": [50],
      "max_depth": [6],
      "learning_rate": [0.1]
    },

    "catboost": {
      "iterations": [50],
      "depth": [6],
      "learning_rate": [0.1]
    },

    "svm": {
      "C": [1],
      "kernel": ["rbf"],
      "gamma": ["scale"]
    },

    "mlp": {
      "hidden_layer_sizes": [[50]],
      "activation": ["relu"],
      "solver": ["adam"],
      "alpha": [0.0001],
      "learning_rate": ["constant"],
      "batch_size": [16],
      "learning_rate_init": [0.001],
      "max_iter": [1000]
    },

    "naivebayes": {}
  },
   "lightgbm": {
    "n_estimators": [100],
    "max_depth": [6],
    "learning_rate": [0.05],
    "num_leaves": [31],
    "min_child_samples": [20]
},
    "extratrees": {
    "n_estimators": [50],
    "max_depth": [10],
    "criterion": ["gini"]
},
    "gradientboosting": {
    "n_estimators": [50],
    "max_depth": [3],
    "learning_rate": [0.1]
},
    "knn": {
    "n_neighbors": [5],
    "weights": ["distance"],
    "metric": ["euclidean"]
},
    "logisticregression": {
    "C": [1],
    "penalty": ["l2"],
    "solver": ["liblinear"]
}
}