config.yml

types:
   [
      "infj",
      "infp",
      "intj",
      "intp",
      "istj",
      "istp",
      "isfp",
      "isfj",
      "enfj",
      "enfp",
      "infj",
      "infp",
      "intj",
      "intp",
      "istj",
      "istp",
      "isfp",
      "isfj",
      "enfj",
      "enfp",
      "entj",
      "entp",
      "estj",
      "estp",
      "esfp",
      "esfj",
   ]
my_stop_words: ["ni", "ti", "ne", "te", "se"]
valid_models: ["LogisticRegression", "RandomForest", "SVC"]
model_parameters:
   tfidf:
      sublinear_tf: True
      min_df: 10
      ngram_range: [1, 2]
   LogisticRegression:
      random_state: 0
      solver: "lbfgs"
      class_weight: Null
      max_iter: 500
   RandomForest:
      n_estimators: 200
      max_depth: 3
      random_state: 0
   SVC:
      C: 1
      gamma: 1
      kernel: "rbf"
file_paths:
   data: "data/mbti_1.csv"
   pipeline:
      LogisticRegression: "models/LogisticRegression.pkl"
      RandomForest: "models/RandomForest.pkl"
      SVC: "models/SVC.pkl"
   accuracy:
      LogisticRegression: "models/lr_accuracy.pkl"
      RandomForest: "models/rf_accuracy.pkl"
      SVC: "models/svc_accuracy.pkl"