refactor(Project): move out load_data to utils, rename fetch_data to run_fetch_data, got classifiers to work (#38)

run_pipeline.py

@@ -1,7 +1,7 @@
 from sklearnex import patch_sklearn
 patch_sklearn()
 
-from load_data import get_crypto_assets, get_etf_assets, load_data
+from utils.load_data import get_crypto_assets, get_etf_assets, load_data
 
 import pandas as pd
 import numpy as np
@@ -19,43 +19,44 @@ from training.pipeline import run_single_asset_trainig_pipeline
 
 # Parameters
 regression_models = [
-    ('Lasso', Lasso(alpha=1.0, max_iter=10000)),
-    ('Ridge', Ridge(alpha=1.0)),
+    # ('Lasso', Lasso(alpha=0.1, max_iter=1000)),
+    ('Ridge', Ridge(alpha=0.1)),
     ('BayesianRidge', BayesianRidge()),
-    ('KNN', KNeighborsRegressor(n_neighbors=15)),
-    # ('AB', AdaBoostRegressor()),
+    ('KNN', KNeighborsRegressor(n_neighbors=25)),
+    # ('AB', AdaBoostRegressor(random_state=1)),
     # ('LR', LinearRegression(n_jobs=-1)),
     # ('MLP', MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000)),
     # ('RF', RandomForestRegressor(n_jobs=-1)),
     # ('SVR', SVR(kernel='rbf', C=1e3, gamma=0.1))
 ]
-ensemble_model = [('Ensemble - Lasso', Lasso(alpha=1.0, max_iter=10000, positive=True))]
+regression_ensemble_model = [('Ensemble - Ridge', Ridge(alpha=0.1))]
 
 classification_models = [
     ('LR', LogisticRegression(n_jobs=-1)),
-    # ('LDA', LinearDiscriminantAnalysis()),
-    # ('KNN', KNeighborsClassifier()),
-    # ('CART', DecisionTreeClassifier()),
-    # ('NB', GaussianNB()),
+    ('LDA', LinearDiscriminantAnalysis()),
+    ('KNN', KNeighborsClassifier()),
+    ('CART', DecisionTreeClassifier()),
+    ('NB', GaussianNB()),
     # ('AB', AdaBoostClassifier()),
     # ('RF', RandomForestClassifier(n_jobs=-1))
 ]
+classification_ensemble_model = [('Ensemble - CART', DecisionTreeClassifier())]
 
 
 path = 'data/'
 all_assets = get_crypto_assets(path)
 
-sliding_window_size = 200
-retrain_every = 100
-scaler = 'none' # 'normalize' 'minmax' 'standardize' 'none'
+sliding_window_size = 150
+retrain_every = 20
+scaler = 'minmax' # 'normalize' 'minmax' 'standardize' 'none'
 include_original_data_in_ensemble = True
-method = 'regression'
+method = 'classification'
 data_parameters = dict(path=path,
     target_asset_lags= [1,2,3,4,5,6,8,10,15],
-    load_other_assets= True,
+    load_other_assets= False,
     other_asset_lags= [],
     log_returns= True,
-    add_date_features= True,
+    add_date_features= False,
     own_technical_features= 'level2',
     other_technical_features= 'none',
     exogenous_features= 'none',
@@ -101,10 +102,10 @@ for asset in all_assets:
     ensemble_result, ensemble_preds = run_single_asset_trainig_pipeline(
         ticker_to_predict = asset,
         X = ensemble_X,
-        y = target_returns,
+        y = y,
         target_returns = target_returns,
-        models = ensemble_model,
-        method = 'regression',
+        models = regression_ensemble_model if method == 'regression' else classification_ensemble_model,
+        method = method,
         sliding_window_size = sliding_window_size,
         retrain_every = retrain_every,
         scaler = scaler