from src import util_funcs
from src.explore import plot_funcs
from src.explore.signatures import sig_models, sig_model_runners
from src.explore.theme_setup import data_path, logs_path, weights_path
from src.explore.theme_setup import generate_theme
# load data and prep
df_20 = pd.read_feather(data_path / 'df_20.feather')
df_20 = df_20.set_index('id')
X_raw, distances, labels = generate_theme(df_20,
'all_towns',
bandwise=True,
max_dist=800)
X_trans = StandardScaler().fit_transform(X_raw)
test_idx = util_funcs.train_test_idxs(df_20, 200) # 200 gives about 25%
# setup paramaters
epochs = 5
batch = 256
theme_base = f'VAE_e{epochs}'
n_d = len(distances)
split_input_dims = (int(2 * n_d), int(9 * n_d), int(2 * n_d))
split_latent_dims = (4, 6, 2)
split_hidden_layer_dims = ([24, 24, 24], [32, 32, 32], [8, 8, 8])
latent_dim = 6
lr = 1e-3
# seed = 0
# beta = 4
# cap = 12
for seed in range(10):
from src.explore import plot_funcs
from src.explore.theme_setup import data_path, logs_path, weights_path
from src.explore.theme_setup import generate_theme
# %%
# load data and prep
df_20 = pd.read_feather(data_path / 'df_20.feather')
df_20 = df_20.set_index('id')
# generate theme
X_raw, distances, labels = generate_theme(df_20, 'pred_lu', bandwise=True)
# transform X
X_trans_all = StandardScaler().fit_transform(X_raw).astype(np.float32)
# get y
y_all = df_20['ac_eating_400'].values
# test split - use spatial splitting - 300 modulo gives about 11%
xy_test_idx = util_funcs.train_test_idxs(df_20, 300)
X_trans_train = X_trans_all[~xy_test_idx]
X_trans_test = X_trans_all[xy_test_idx]
y_train = y_all[~xy_test_idx]
y_test = y_all[xy_test_idx]
# validation split - 200 modulo gives about 25%
xy_val_idx = util_funcs.train_test_idxs(df_20[~xy_test_idx], 200)
X_trans_val = X_trans_train[
xy_val_idx] # do first before repurposing variable name
X_trans_train = X_trans_train[~xy_val_idx]
y_val = y_train[xy_val_idx] # do first before repurposing variable name
y_train = y_train[~xy_val_idx]
# %%
epochs = 100
reg = pred_models.LandUsePredictor(theme_base=f'eating_e{epochs}')