@misc{lai2020tods,
    title={TODS: An Automated Time Series Outlier Detection System},
    author={Kwei-Harng Lai and Daochen Zha and Guanchu Wang and Junjie Xu and Yue Zhao and Devesh Kumar and Yile Chen and Purav Zumkhawaka and Minyang Wan and Diego Martinez and Xia Hu},
    year={2020},
    eprint={2009.09822},
    archivePrefix={arXiv},
    primaryClass={cs.DB}
}

sudo apt-get install libssl-dev libcurl4-openssl-dev libyaml-dev build-essential libopenblas-dev libcap-dev ffmpeg

git clone https://github.com/datamllab/tods.git

cd tods
pip install -e .

import pandas as pd

from tods import schemas as schemas_utils
from tods import generate_dataset, evaluate_pipeline

table_path = 'datasets/anomaly/raw_data/yahoo_sub_5.csv'
target_index = 6 # what column is the target
metric = 'F1_MACRO' # F1 on both label 0 and 1

# Read data and generate dataset
df = pd.read_csv(table_path)
dataset = generate_dataset(df, target_index)

# Load the default pipeline
pipeline = schemas_utils.load_default_pipeline()

# Run the pipeline
pipeline_result = evaluate_pipeline(dataset, pipeline, metric)
print(pipeline_result)

import pandas as pd

from axolotl.backend.simple import SimpleRunner

from tods import generate_dataset, generate_problem
from tods.searcher import BruteForceSearch

# Some information
table_path = 'datasets/yahoo_sub_5.csv'
target_index = 6 # what column is the target
time_limit = 30 # How many seconds you wanna search
metric = 'F1_MACRO' # F1 on both label 0 and 1

# Read data and generate dataset and problem
df = pd.read_csv(table_path)
dataset = generate_dataset(df, target_index=target_index)
problem_description = generate_problem(dataset, metric)

# Start backend
backend = SimpleRunner(random_seed=0)

# Start search algorithm
search = BruteForceSearch(problem_description=problem_description,
                          backend=backend)

# Find the best pipeline
best_runtime, best_pipeline_result = search.search_fit(input_data=[dataset], time_limit=time_limit)
best_pipeline = best_runtime.pipeline
best_output = best_pipeline_result.output

# Evaluate the best pipeline
best_scores = search.evaluate(best_pipeline).scores