intents_sample_json.json

{
  "dataset": {
    "type": "classification",
    "format": "json",
    "orient": "records",
    "lines": true,
    "data_path": "sample",
    "train": "sample.json",
    "x": "text",
    "y": "intents",
    "url": "http://lnsigo.mipt.ru/export/datasets/snips_intents/train.json",
    "seed": 42,
    "field_to_split": "train",
    "split_fields": [
      "train",
      "valid"
    ],
    "split_proportions": [
      0.9,
      0.1
    ]
  },
  "chainer": {
    "in": [
      "x"
    ],
    "in_y": [
      "y"
    ],
    "pipe": [
      {
        "id": "classes_vocab",
        "name": "default_vocab",
        "fit_on": [
          "y"
        ],
        "level": "token",
        "save_path": "vocabs/snips_classes.dict",
        "load_path": "vocabs/snips_classes.dict"
      },
      {
        "id": "my_embedder",
        "name": "fasttext",
        "save_path": "embeddings/dstc2_fastText_model.bin",
        "load_path": "embeddings/dstc2_fastText_model.bin",
        "dim": 100
      },
      {
        "id": "my_tokenizer",
        "name": "nltk_tokenizer",
        "tokenizer": "wordpunct_tokenize"
      },
      {
        "in": [
          "x"
        ],
        "in_y": [
          "y"
        ],
        "out": [
          "y_labels",
          "y_probas_dict"
        ],
        "main": true,
        "name": "intent_model",
        "save_path": "intents/intent_cnn_snips_v4",
        "load_path": "intents/intent_cnn_snips_v4",
        "classes": "#classes_vocab.keys()",
        "kernel_sizes_cnn": [
          1,
          2,
          3
        ],
        "filters_cnn": 256,
        "confident_threshold": 0.5,
        "optimizer": "Adam",
        "lear_rate": 0.01,
        "lear_rate_decay": 0.1,
        "loss": "binary_crossentropy",
        "text_size": 15,
        "coef_reg_cnn": 1e-4,
        "coef_reg_den": 1e-4,
        "dropout_rate": 0.5,
        "dense_size": 100,
        "model_name": "cnn_model",
        "embedder": "#my_embedder",
        "tokenizer": "#my_tokenizer"
      }
    ],
    "out": [
      "y_labels",
      "y_probas_dict"
    ]
  },
  "train": {
    "epochs": 100,
    "batch_size": 64,
    "metrics": [
      "classification_accuracy",
      "classification_f1",
      "classification_roc_auc"
    ],
    "validation_patience": 5,
    "val_every_n_epochs": 1,
    "log_every_n_epochs": 1,
    "show_examples": false,
    "validate_best": true,
    "test_best": false
  },
  "metadata": {
    "labels": {
      "telegram_utils": "IntentModel",
      "server_utils": "KerasIntentModel"
    },
    "download": [
      "http://lnsigo.mipt.ru/export/deeppavlov_data/intents.tar.gz",
      "http://lnsigo.mipt.ru/export/deeppavlov_data/vocabs.tar.gz",
      {
        "url": "http://lnsigo.mipt.ru/export/datasets/snips_intents/train.json",
        "subdir": "sample"
      },
      {
        "url": "http://lnsigo.mipt.ru/export/deeppavlov_data/embeddings/dstc2_fastText_model.bin",
        "subdir": "embeddings"
      }
    ]
  }
}