keystroke-scripts/config_test_computer_engine.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
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
{
  "dataset_path": "dataset_3_full_with_outliers_IL_filtered.csv",
  "early_stopping": false,
  "seeds": [42, 123, 456],
  "output_affix": "gcloud-instance-dataset3",
  "show_class_distributions": false,
  "draw_feature_importance": true,
  "debug": false,
  "use_gpu": true,

  "models_to_train": [
    "RandomForest",
    "XGBoost",
    "CatBoost",
    "SVM",
    "MLP",
    "NaiveBayes",
    "LightGBM",
    "ExtraTrees",
    "GradientBoosting",
    "KNN",
    "LogisticRegression"
  ],

  "experiments": [
    {"name": "FI_vs_T", "platform": true, "train": [1, 2], "test": 3},
    {"name": "FT_vs_I", "platform": true, "train": [1, 3], "test": 2},
    {"name": "IT_vs_F", "platform": true, "train": [2, 3], "test": 1},
    {"name": "F_vs_I", "platform": true, "train": [1], "test": 2},
    {"name": "F_vs_T", "platform": true, "train": [1], "test": 3},
    {"name": "I_vs_F", "platform": true, "train": [2], "test": 1},
    {"name": "I_vs_T", "platform": true, "train": [2], "test": 3},
    {"name": "T_vs_F", "platform": true, "train": [3], "test": 1},
    {"name": "T_vs_I", "platform": true, "train": [3], "test": 2},

    {"name": "S1_vs_S2_All", "session": true, "platform": "all", "train": [1], "test": 2},
    {"name": "S1_vs_S2_P1", "session": true, "platform": 1, "train": [1], "test": 2},
    {"name": "S1_vs_S2_P2", "session": true, "platform": 2, "train": [1], "test": 2},
    {"name": "S1_vs_S2_P3", "session": true, "platform": 3, "train": [1], "test": 2}

  ],

  "param_grids": {
    "randomforest": {
      "n_estimators": [100, 300, 500],
      "max_depth": [10, 20, null],
      "min_samples_split": [2, 10],
      "min_samples_leaf": [1, 2],
      "max_features": ["sqrt", "log2"],
      "bootstrap": [true, false]
    },

    "xgboost": {
      "n_estimators": [100, 200],
      "max_depth": [4, 6, 8],
      "learning_rate": [0.05, 0.1],
      "subsample": [0.8, 1.0],
      "colsample_bytree": [0.8, 1.0],
      "reg_lambda": [1, 3]
    },

    "catboost": {
      "iterations": [100, 200],
      "depth": [4, 6, 8],
      "learning_rate": [0.05, 0.1],
      "l2_leaf_reg": [1, 3, 5],
      "border_count": [32, 64]
    },

    "svm": {
      "decision_function_shape": ["ovo", "ovr"],
      "C": [0.1, 1, 10, 100],
      "kernel": ["rbf", "linear", "poly", "sigmoid"],
      "gamma": ["scale", "auto"]
    },

    "mlp": {
      "hidden_layer_sizes": [[50], [100], [50, 50]],
      "activation": ["relu", "tanh"],
      "solver": ["adam"],
      "alpha": [0.0001, 0.001],
      "learning_rate": ["constant", "adaptive"],
      "batch_size": [36, 16, 8, 2, 1],
      "learning_rate_init": [0.001, 0.01],
      "max_iter": [2000]
    },

    "naivebayes": {}
  },
    "lightgbm": {
    "n_estimators": [100, 200],
    "max_depth": [6, 8, -1],
    "learning_rate": [0.05, 0.1],
    "num_leaves": [31, 50],
    "min_child_samples": [20, 30]
},
    "extratrees": {
    "n_estimators": [100, 300, 500],
    "max_depth": [10, 20, null],
    "min_samples_split": [2, 10],
    "min_samples_leaf": [1, 2],
    "max_features": ["sqrt", "log2"],
    "bootstrap": [false],
    "criterion": ["gini", "entropy"]
},
    "gradientboosting": {
    "n_estimators": [100, 200, 300],
    "max_depth": [3, 5, 7],
    "learning_rate": [0.05, 0.1, 0.15],
    "min_samples_split": [2, 10, 20],
    "min_samples_leaf": [1, 5, 10],
    "subsample": [0.8, 1.0],
    "max_features": ["sqrt", "log2", null]
},
    "knn": {
    "n_neighbors": [3, 5, 7, 10, 15],
    "weights": ["uniform", "distance"],
    "metric": ["euclidean", "manhattan", "cosine"],
    "algorithm": ["auto", "ball_tree", "kd_tree"]
},
    "logisticregression": {
    "C": [0.001, 0.01, 0.1, 1, 10, 100],
    "penalty": ["l2", "l1"],
    "solver": ["liblinear", "saga"],
    "max_iter": [3000, 2000]
}
}