You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
80 lines
2.0 KiB
Python
80 lines
2.0 KiB
Python
# %%
|
|
import pandas as pd
|
|
from itertools import product
|
|
|
|
|
|
def get_state_vect_cols(prefix=''):
|
|
if prefix:
|
|
prefix += '_'
|
|
vectors = ['r', 'v']
|
|
components = ['x', 'y', 'z']
|
|
col_names = [f'{prefix}{v}_{c}' for v, c in product(vectors, components)]
|
|
return col_names
|
|
|
|
|
|
# %%
|
|
df = pd.read_parquet("data.pq")
|
|
|
|
# %%
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
feature_cols = ['elapsed_seconds'
|
|
] + get_state_vect_cols('pred') + get_state_vect_cols('start')
|
|
target_cols = get_state_vect_cols('err')
|
|
X = df[feature_cols]
|
|
y = df[target_cols]
|
|
data_keys = ['X_train', 'X_test', 'y_train', 'y_test']
|
|
data_vals = train_test_split(X, y, test_size=0.2)
|
|
train_test_data = dict(zip(data_keys, data_vals))
|
|
# %%
|
|
from sklearn.utils.validation import check_X_y
|
|
import joblib
|
|
|
|
from catboost import CatBoostRegressor
|
|
|
|
|
|
def train_model():
|
|
X, ys = train_test_data['X_train'], train_test_data['y_train']
|
|
check_X_y(X, ys, multi_output=True)
|
|
models = {}
|
|
|
|
for target_col in ys.columns:
|
|
y1 = ys[target_col]
|
|
print(X.shape, y1.shape)
|
|
reg = CatBoostRegressor()
|
|
reg.fit(X, y1)
|
|
models[target_col] = reg
|
|
print(target_col)
|
|
joblib.dump(models, f"models/{CatBoostRegressor.__name__}.model")
|
|
|
|
|
|
# train_model()
|
|
# %%
|
|
from sklearn import metrics
|
|
|
|
|
|
def eval_model():
|
|
models = joblib.load(f"models/{CatBoostRegressor.__name__}.model")
|
|
X, ys = train_test_data['X_test'], train_test_data['y_test']
|
|
evals = []
|
|
for target_col, reg in models.items():
|
|
y_hat = reg.predict(X) # fake
|
|
y = ys[target_col] # real
|
|
dy = (y - y_hat).abs()
|
|
rmse = metrics.mean_squared_error(y, y_hat, squared=False)
|
|
r2 = metrics.r2_score(y, y_hat)
|
|
eval_dict = {
|
|
'Error': target_col,
|
|
'RMSE': rmse,
|
|
'R^2': r2,
|
|
"err_max": dy.max(),
|
|
"err_min": dy.min(),
|
|
"err_mean": dy.mean(),
|
|
}
|
|
evals.append(eval_dict)
|
|
print(pd.DataFrame(evals))
|
|
|
|
|
|
eval_model()
|
|
# %%
|