def cartesian_params(self):
return list(
product_dict(fraction=self.fraction,
contamination=self.contamination,
seed=self.seed))
def cartesian_params(self):
return product_dict(min_cluster_size=self.min_cluster_size,
allow_noise=self.allow_noise)
def cartesian_params(self):
return product_dict(**self.kwargs)
for i in outliers]
one_to_many = [(inliers, [j for j in outliers
if j == i], [], [j for j in outliers if j != i])
for i in outliers]
# how many samples per class are used for all tests
n_classes = [8000]
test_size = 8000
# %%
param_combinations = product_dict(**dict(seed=range(3),
labeled_data=[1.0],
fixed_cont=[0.1],
n_oe=[False, 50, 250],
use_nn=[True],
use_umap=[False],
min_len=[200],
epochs=[15],
class_split=standard_split,
weakly_supervised=[False]))
# split the outlier, inlier tuple pairs and print all parameters for run
for d in param_combinations:
d["inliers"], d["outliers"], d["test_inliers"], d["test_outliers"] = d[
"class_split"]
d.pop('pair', None)
d["in_test_not_train_outlier"] = [
x for x in d["test_outliers"] if x not in d["outliers"]
]
print(param_combinations)
def main():
standard_split = [
([0, 1, 2, 11], [3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15])]
pairwise_split = list(permutations([[x] for x in range(0, 16)], 2))
# %%
param_combinations = product_dict(**dict(
seed=[42, 43, 44],
test_size=[0.2],
labeled_data=[0.1, 0.3, 0.5, 0.8, 1.0],
fixed_cont=[0.05, 0.1],
n_oe=[0],
use_nn=[True],
pair=standard_split
))
# how many samples per class are used for all tests
n_class = 3000
# split the outlier, inlier tuple pairs and print all parameters for run
for d in param_combinations:
d["inliers"], d["outliers"] = d["pair"]
d.pop('pair', None)
#data_path = "/home/philipp/projects/dad4td/data/processed/20_news_imdb_vec.pkl"
data_path = "/home/philipp/projects/dad4td/data/raw/QS-OCR-Large/rvl_cdip.pkl"
oe_path = "/home/philipp/projects/dad4td/data/processed/oe_data.pkl"
res_path = next_path(
"/home/philipp/projects/dad4td/reports/semisupervised/semisup_rvl_pw_%04d.tsv")
doc2vec_model = Doc2VecModel("apnews", "apnews", 1.0,
100, 1,
"/home/philipp/projects/dad4td/models/apnews_dbow/doc2vec.bin")
# load data and get the doc2vec vectors for all of the data used
df_full = pd.read_pickle(data_path)
# sample only a portion of the data
df_full = df_full.groupby('target', group_keys=False).apply(
lambda df: df.sample(n=n_class, random_state=42))
# %%
df_full["vecs"] = doc2vec_model.vectorize(df_full["text"])
df_full["vecs"] = df_full["vecs"].apply(tuple)
# %%
result_df = pd.DataFrame()
for i, params in enumerate(param_combinations):
print(
f"\n\n---------------------\n\nRun {i+1} out of {len(param_combinations)}\n\n{params}")
df, df_test = prepare_data(df_full, **params)
# UMAP Train
docvecs, umap_model = umap_reduce(
df["vecs"].to_list(), df["label"], None, **params)
# Ivis
docvecs, ivis_model = ivis_reduce(
docvecs, df["label"], None, **params)
# remove OE data, so it's not scored as well
df["decision_scores"] = docvecs
df = df.where(df.scorable == 1).dropna()
# find outliers in 1D scores
preds, iqr_model = score_out_preds(df["decision_scores"], None,
contamination=df.outlier_label.value_counts(normalize=True)[-1])
# score the predictions for outliers
scores = get_scores(dict(), df["outlier_label"], preds)
# %%
# write the scores to df and save
scores.update(params)
scores["data"] = "train"
result_df = result_df.append(scores, ignore_index=True)
result_df.to_csv(res_path, sep="\t")
print(f"\nTraining scores:\n{pd.DataFrame([scores], index=[0])}")
# %%
# test UMAP and ivis
docvecs_test, _ = umap_reduce(
df_test["vecs"].to_list(), None, umap_model, **params)
docvecs_test, _ = ivis_reduce(docvecs_test, None, ivis_model, **params)
# remove OE data, so it's not scored as well
df_test["decision_scores"] = docvecs_test
df_test = df_test.where(df_test.scorable == 1).dropna()
# find outliers in 1D scores
preds = iqr_model.transform(
df_test["decision_scores"], thresh_factor=1)
# score the predictions for outliers
scores = get_scores(dict(), df_test["outlier_label"], preds)
# write the scores to df and save
scores.update(params)
scores["data"] = "test"
result_df = result_df.append(scores, ignore_index=True)
result_df.to_csv(res_path, sep="\t")
print(f"\nTest scores:\n{pd.DataFrame([scores], index=[0])}")
import argparse
from ModelHelper import ModelHelper
from utils import product_dict
from tqdm import tqdm
# Multiple configuration trainer
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model_name", nargs="+", type=str)
parser.add_argument("--nb_hidden", nargs="+", type=int)
parser.add_argument("--window_size", nargs="+", type=int)
parser.add_argument("--stride", nargs="+", type=int)
args = parser.parse_args()
helper = ModelHelper("beatles.txt")
configs = list(product_dict(**args.__dict__))
for config in tqdm(configs):
helper.build(config["window_size"], config["stride"])
model = helper.create_model(config["model_name"], config["nb_hidden"])
print(helper._label(config))
history = helper.train(model, nb_epochs=100, verbose=0)
helper.plot_history(history, config)
helper.plot_history(configs=args.__dict__, show_plot=True)