fix: notebooks
This commit is contained in:
@@ -1,412 +0,0 @@
|
||||
baseline_experiments:
|
||||
# BiGRU Models (GPU-enabled)
|
||||
- name: "bigru"
|
||||
description: "Baseline BiGRU with full name features (GPU)"
|
||||
model_type: "bigru"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
embedding_dim: 64
|
||||
gru_units: 32
|
||||
epochs: 2
|
||||
batch_size: 32
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "bigru", "gpu" ]
|
||||
|
||||
- name: "bigru_native"
|
||||
description: "Baseline BiGRU with native name features (GPU)"
|
||||
model_type: "bigru"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
embedding_dim: 64
|
||||
gru_units: 32
|
||||
epochs: 2
|
||||
batch_size: 32
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "bigru", "native", "gpu" ]
|
||||
|
||||
- name: "bigru_surname"
|
||||
description: "Baseline BiGRU with surname features (GPU)"
|
||||
model_type: "bigru"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
embedding_dim: 64
|
||||
gru_units: 32
|
||||
epochs: 2
|
||||
batch_size: 32
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "bigru", "surname", "gpu" ]
|
||||
|
||||
## CNN Models (GPU-enabled)
|
||||
- name: "cnn"
|
||||
description: "Baseline CNN with character patterns (GPU)"
|
||||
model_type: "cnn"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
embedding_dim: 64
|
||||
filters: 64
|
||||
kernel_size: 3
|
||||
dropout: 0.5
|
||||
epochs: 2
|
||||
batch_size: 32
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "cnn", "gpu" ]
|
||||
|
||||
- name: "cnn_native"
|
||||
description: "Baseline CNN with native name character patterns (GPU)"
|
||||
model_type: "cnn"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
embedding_dim: 64
|
||||
filters: 64
|
||||
kernel_size: 3
|
||||
dropout: 0.5
|
||||
epochs: 2
|
||||
batch_size: 32
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "cnn", "native", "gpu" ]
|
||||
|
||||
- name: "cnn_surname"
|
||||
description: "Baseline CNN with surname character patterns (GPU)"
|
||||
model_type: "cnn"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
embedding_dim: 64
|
||||
filters: 64
|
||||
kernel_size: 3
|
||||
dropout: 0.5
|
||||
epochs: 2
|
||||
batch_size: 32
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "cnn", "surname", "gpu" ]
|
||||
|
||||
## Ensemble Models (CPU)
|
||||
- name: "ensemble"
|
||||
description: "Baseline Ensemble with multiple models"
|
||||
model_type: "ensemble"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
base_models: [ "logistic_regression", "random_forest", "xgboost" ]
|
||||
voting: "soft"
|
||||
cv_folds: 5
|
||||
tags: [ "baseline", "ensemble" ]
|
||||
|
||||
- name: "ensemble_native"
|
||||
description: "Baseline Ensemble with native name"
|
||||
model_type: "ensemble"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
base_models: [ "logistic_regression", "random_forest", "xgboost" ]
|
||||
voting: "soft"
|
||||
cv_folds: 5
|
||||
tags: [ "baseline", "ensemble", "native" ]
|
||||
|
||||
- name: "ensemble_surname"
|
||||
description: "Baseline Ensemble with surname"
|
||||
model_type: "ensemble"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
base_models: [ "logistic_regression", "random_forest", "xgboost" ]
|
||||
voting: "soft"
|
||||
cv_folds: 5
|
||||
tags: [ "baseline", "ensemble", "surname" ]
|
||||
|
||||
# LightGBM Models (GPU-enabled)
|
||||
- name: "lightgbm"
|
||||
description: "Baseline LightGBM with engineered features (GPU)"
|
||||
model_type: "lightgbm"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: -1
|
||||
learning_rate: 0.1
|
||||
num_leaves: 31
|
||||
subsample: 0.8
|
||||
colsample_bytree: 0.8
|
||||
use_gpu: true
|
||||
tags: [ "baseline", "lightgbm", "gpu" ]
|
||||
|
||||
- name: "lightgbm_native"
|
||||
description: "Baseline LightGBM with native name features (GPU)"
|
||||
model_type: "lightgbm"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: -1
|
||||
learning_rate: 0.1
|
||||
num_leaves: 31
|
||||
subsample: 0.8
|
||||
colsample_bytree: 0.8
|
||||
use_gpu: true
|
||||
tags: [ "baseline", "lightgbm", "native", "gpu" ]
|
||||
|
||||
- name: "lightgbm_surname"
|
||||
description: "Baseline LightGBM with surname features (GPU)"
|
||||
model_type: "lightgbm"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: -1
|
||||
learning_rate: 0.1
|
||||
num_leaves: 31
|
||||
subsample: 0.8
|
||||
colsample_bytree: 0.8
|
||||
use_gpu: true
|
||||
tags: [ "baseline", "lightgbm", "surname", "gpu" ]
|
||||
|
||||
# Logistic Regression Models (CPU)
|
||||
- name: "logistic_regression"
|
||||
description: "Baseline logistic regression with full name"
|
||||
model_type: "logistic_regression"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
max_features: 10000
|
||||
tags: [ "baseline", "logistic_regression", "fullname" ]
|
||||
|
||||
- name: "logistic_regression_native"
|
||||
description: "Logistic regression with native name only"
|
||||
model_type: "logistic_regression"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "logistic_regression", "native" ]
|
||||
|
||||
- name: "logistic_regression_surname"
|
||||
description: "Logistic regression with surname name only"
|
||||
model_type: "logistic_regression"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "logistic_regression", "surname" ]
|
||||
|
||||
# LSTM Models (GPU-enabled)
|
||||
- name: "lstm"
|
||||
description: "Baseline LSTM with full name features (GPU)"
|
||||
model_type: "lstm"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
embedding_dim: 128
|
||||
lstm_units: 64
|
||||
epochs: 2
|
||||
batch_size: 64
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "lstm", "gpu" ]
|
||||
|
||||
- name: "lstm_native"
|
||||
description: "Baseline LSTM with native name features (GPU)"
|
||||
model_type: "lstm"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
embedding_dim: 128
|
||||
lstm_units: 64
|
||||
epochs: 2
|
||||
batch_size: 64
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "lstm", "native", "gpu" ]
|
||||
|
||||
- name: "lstm_surname"
|
||||
description: "Baseline LSTM with surname features (GPU)"
|
||||
model_type: "lstm"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
embedding_dim: 128
|
||||
lstm_units: 64
|
||||
epochs: 2
|
||||
batch_size: 64
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "lstm", "surname", "gpu" ]
|
||||
|
||||
# Naive Bayes Models (CPU)
|
||||
- name: "naive_bayes"
|
||||
description: "Baseline Naive Bayes with full name features"
|
||||
model_type: "naive_bayes"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "naive_bayes" ]
|
||||
|
||||
- name: "naive_bayes_native"
|
||||
description: "Baseline Naive Bayes with native name features"
|
||||
model_type: "naive_bayes"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "naive_bayes", "native" ]
|
||||
|
||||
- name: "naive_bayes_surname"
|
||||
description: "Baseline Naive Bayes with surname features"
|
||||
model_type: "naive_bayes"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "naive_bayes", "surname" ]
|
||||
|
||||
# Random Forest Models (CPU)
|
||||
- name: "random_forest"
|
||||
description: "Baseline Random Forest with engineered features"
|
||||
model_type: "random_forest"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: 10
|
||||
min_samples_split: 2
|
||||
min_samples_leaf: 1
|
||||
tags: [ "baseline", "random_forest", "engineered" ]
|
||||
|
||||
- name: "random_forest_native"
|
||||
description: "Baseline Random Forest with native name engineered features"
|
||||
model_type: "random_forest"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: 10
|
||||
min_samples_split: 2
|
||||
min_samples_leaf: 1
|
||||
tags: [ "baseline", "random_forest", "engineered", "native" ]
|
||||
|
||||
- name: "random_forest_surname"
|
||||
description: "Baseline Random Forest with surname engineered features"
|
||||
model_type: "random_forest"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: 10
|
||||
min_samples_split: 2
|
||||
min_samples_leaf: 1
|
||||
tags: [ "baseline", "random_forest", "engineered", "surname" ]
|
||||
|
||||
# SVM Models (CPU)
|
||||
- name: "svm"
|
||||
description: "Baseline SVM with full name features"
|
||||
model_type: "svm"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
C: 1.0
|
||||
kernel: "rbf"
|
||||
ngram_range: [ 2, 4 ]
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "svm" ]
|
||||
|
||||
- name: "svm_native"
|
||||
description: "Baseline SVM with native name features"
|
||||
model_type: "svm"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
C: 1.0
|
||||
kernel: "rbf"
|
||||
ngram_range: [ 2, 4 ]
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "svm", "native" ]
|
||||
|
||||
- name: "svm_surname"
|
||||
description: "Baseline SVM with surname features"
|
||||
model_type: "svm"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
C: 1.0
|
||||
kernel: "rbf"
|
||||
ngram_range: [ 2, 4 ]
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "svm", "surname" ]
|
||||
|
||||
# Transformer Models (GPU-enabled)
|
||||
- name: "transformer"
|
||||
description: "Baseline Transformer with attention mechanism (GPU)"
|
||||
model_type: "transformer"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
embedding_dim: 128
|
||||
num_heads: 4
|
||||
num_layers: 2
|
||||
epochs: 2
|
||||
batch_size: 64
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "transformer", "gpu" ]
|
||||
|
||||
- name: "transformer_native"
|
||||
description: "Baseline Transformer with native name attention mechanism (GPU)"
|
||||
model_type: "transformer"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
embedding_dim: 128
|
||||
num_heads: 4
|
||||
num_layers: 2
|
||||
epochs: 2
|
||||
batch_size: 64
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "transformer", "native", "gpu" ]
|
||||
|
||||
- name: "transformer_surname"
|
||||
description: "Baseline Transformer with surname attention mechanism (GPU)"
|
||||
model_type: "transformer"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
embedding_dim: 128
|
||||
num_heads: 4
|
||||
num_layers: 2
|
||||
epochs: 2
|
||||
batch_size: 64
|
||||
use_gpu: true
|
||||
mixed_precision: true
|
||||
tags: [ "baseline", "neural", "transformer", "surname", "gpu" ]
|
||||
|
||||
# XGBoost Models (GPU-enabled)
|
||||
- name: "xgboost"
|
||||
description: "Baseline XGBoost with engineered features (GPU)"
|
||||
model_type: "xgboost"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: 6
|
||||
learning_rate: 0.1
|
||||
subsample: 0.8
|
||||
colsample_bytree: 0.8
|
||||
use_gpu: true
|
||||
tags: [ "baseline", "xgboost", "gpu" ]
|
||||
|
||||
- name: "xgboost_native"
|
||||
description: "Baseline XGBoost with native name engineered features (GPU)"
|
||||
model_type: "xgboost"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: 6
|
||||
learning_rate: 0.1
|
||||
subsample: 0.8
|
||||
colsample_bytree: 0.8
|
||||
use_gpu: true
|
||||
tags: [ "baseline", "xgboost", "native", "gpu" ]
|
||||
|
||||
- name: "xgboost_surname"
|
||||
description: "Baseline XGBoost with surname engineered features (GPU)"
|
||||
model_type: "xgboost"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
n_estimators: 100
|
||||
max_depth: 6
|
||||
learning_rate: 0.1
|
||||
subsample: 0.8
|
||||
colsample_bytree: 0.8
|
||||
use_gpu: true
|
||||
tags: [ "baseline", "xgboost", "surname", "gpu" ]
|
||||
|
||||
|
||||
# Advanced Experiments Configuration
|
||||
advanced_experiments:
|
||||
|
||||
# Feature Study Configurations
|
||||
feature_studies:
|
||||
|
||||
# Hyperparameter Tuning Configurations
|
||||
hyperparameter_tuning:
|
||||
|
||||
@@ -73,37 +73,6 @@ baseline_experiments:
|
||||
batch_size: 32
|
||||
tags: [ "baseline", "neural", "cnn", "surname" ]
|
||||
|
||||
## Ensemble Models
|
||||
- name: "ensemble"
|
||||
description: "Baseline Ensemble with multiple models"
|
||||
model_type: "ensemble"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
base_models: [ "logistic_regression", "random_forest", "xgboost" ]
|
||||
voting: "soft"
|
||||
cv_folds: 5
|
||||
tags: [ "baseline", "ensemble" ]
|
||||
|
||||
- name: "ensemble_native"
|
||||
description: "Baseline Ensemble with native name"
|
||||
model_type: "ensemble"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
base_models: [ "logistic_regression", "random_forest", "xgboost" ]
|
||||
voting: "soft"
|
||||
cv_folds: 5
|
||||
tags: [ "baseline", "ensemble", "native" ]
|
||||
|
||||
- name: "ensemble_surname"
|
||||
description: "Baseline Ensemble with surname"
|
||||
model_type: "ensemble"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
base_models: [ "logistic_regression", "random_forest", "xgboost" ]
|
||||
voting: "soft"
|
||||
cv_folds: 5
|
||||
tags: [ "baseline", "ensemble", "surname" ]
|
||||
|
||||
# LightGBM Models
|
||||
- name: "lightgbm"
|
||||
description: "Baseline LightGBM with engineered features"
|
||||
@@ -262,40 +231,6 @@ baseline_experiments:
|
||||
min_samples_leaf: 1
|
||||
tags: [ "baseline", "random_forest", "engineered", "surname" ]
|
||||
|
||||
# SVM Models
|
||||
- name: "svm"
|
||||
description: "Baseline SVM with full name features"
|
||||
model_type: "svm"
|
||||
features: [ "full_name" ]
|
||||
model_params:
|
||||
C: 1.0
|
||||
kernel: "rbf"
|
||||
ngram_range: [ 2, 4 ]
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "svm" ]
|
||||
|
||||
- name: "svm_native"
|
||||
description: "Baseline SVM with native name features"
|
||||
model_type: "svm"
|
||||
features: [ "native_name" ]
|
||||
model_params:
|
||||
C: 1.0
|
||||
kernel: "rbf"
|
||||
ngram_range: [ 2, 4 ]
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "svm", "native" ]
|
||||
|
||||
- name: "svm_surname"
|
||||
description: "Baseline SVM with surname features"
|
||||
model_type: "svm"
|
||||
features: [ "surname" ]
|
||||
model_params:
|
||||
C: 1.0
|
||||
kernel: "rbf"
|
||||
ngram_range: [ 2, 4 ]
|
||||
max_features: 5000
|
||||
tags: [ "baseline", "svm", "surname" ]
|
||||
|
||||
# Transformer Models
|
||||
- name: "transformer"
|
||||
description: "Baseline Transformer with attention mechanism"
|
||||
|
||||
Reference in New Issue
Block a user