import os

####### pieline parameters ################
#cluster_sets = ['KMeans', 'LDA', 'HDBSCAN', 'GSDPMM', 'German_BERT', 'Patho_BERT', 'top2vec']
cluster_sets = ['HDBSCAN']

# params:
path2corpus_bow_preprocessed = 'database/bow_prepro_desc.pkl'
path2corpus_embedding_preprocessed = 'database/embedding_prepro_desc.pkl'


#check working directory:
workdir = os.getcwd()
if not workdir[-len('nlp-in-diagnostic-texts-from-nephropathology'):] == 'nlp-in-diagnostic-texts-from-nephropathology':
    print(workdir + " is the wrong working directory.")
    print("please make shure to run this script with working directory '.../path/to/nlp-in-diagnostic-texts-from-nephropathology'.")
    exit(1)

for cluster_set in cluster_sets:
    script_queue = [
        f"python TextClassification/bow_classification.py --clustered_data {cluster_set} --path2corpus {path2corpus_bow_preprocessed}",
        f"python TextClassification/RNN_classification.py --clustered_data {cluster_set} --path2corpus {path2corpus_embedding_preprocessed}",
        f"python TextClassification/CNN_classification.py --clustered_data {cluster_set} --path2corpus {path2corpus_embedding_preprocessed}",
        #f"python TextClassification/bert_classification.py --clustered_data {cluster_set} --path2corpus {path2corpus_embedding_preprocessed}",
        f"python TextClassification/print_classification_metrics.py --clustered_data {cluster_set}"
    ]

    for script in script_queue:
        print("\n########################################### executing ###########################################")
        print(script)
        print("####################################################################################################\n")
        os.system(script)