print("Number of data used for testing", len(csv.index))
# DATA PREPARATION:
# 1. cut to certain Pitching position?
if len(cfg.position) > 0:
assert cfg.position == "Windup" or cfg.position == "Stretch", "Wrong pitching position filtering in config file"
csv = csv[csv["Pitching Position (P)"] == cfg.position]
print("Only pitching position ", cfg.position, "included in data")
# 2. the pitch type "eephus" is excluded because it only occurs once in the data
if label_name == "Pitch Type":
csv = csv[csv["Pitch Type"] != "Eephus"]
# 3. cut to the 5 players with most data
if cfg.five_players:
csv = Tools.cut_csv_to_pitchers(csv)
print("Only the five players with most data are included")
# GET DATA
data, labels = Tools.get_data_from_csv(csv,
label_name,
min_length=cfg.nr_frames)
print("Data shape:", data.shape)
# data = np.load("data_test.npy")
# labels = np.load("labels_test.npy")
# 4. Change labels to super classes (only for the pitch type!)
if cfg.super_classes:
labels = Tools.labels_to_classes(labels)
print("Labels are transformed to superclasses")
