import os, sys

# params:
path2corpus_bow_preprocessed_diagnosis = 'data/bow_prepro_diag.pkl'
path2corpus_embedding_preprocessed_diagnosis = 'data/embedding_prepro_diag.pkl'

# check if we are at correct 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)


# Construct clustering pipeline. This is a suggestion how to use all the scripts.
# I also recommend to run each clustering script one by on to fintune the clusterings (with argument --find_k_value)
script_queue = [
f"python TextClustering/basedOn_BOW/kmeans_Diagnosis.py --path2corpus {path2corpus_bow_preprocessed_diagnosis} --k_value {10}",
f"python TextClustering/basedOn_BOW/LDA_Diagnosis.py --path2corpus {path2corpus_bow_preprocessed_diagnosis} --k_value {12}",
f"python TextClustering/basedOn_BOW/HDBSCAN_Diagnosis.py --path2corpus {path2corpus_bow_preprocessed_diagnosis} --k_value {10}",
f"python TextClustering/basedOn_BOW/GSDPMM_Diagnosis.py --path2corpus {path2corpus_bow_preprocessed_diagnosis} --k_value {14}",

f"python TextClustering/basedOn_Embedding/BERT_Diagnosis.py --path2corpus {path2corpus_embedding_preprocessed_diagnosis} --do_embedding --model2use German_BERT --k_value {17}",
f"python TextClustering/basedOn_Embedding/BERT_Diagnosis.py --path2corpus {path2corpus_embedding_preprocessed_diagnosis} --do_embedding --model2use Patho_BERT --k_value {8}",
f"python TextClustering/basedOn_Embedding/top2vec_Diagnosis.py --path2corpus {path2corpus_embedding_preprocessed_diagnosis} --model2use doc2vec --k_value {7}",

"python TextClustering/cluster_scores2latextable.py",
"python TextClustering/plot_clustersets.py",
"python TextClustering/generate_topicwords.py",
"python TextClustering/clusterset_histos.py"
]

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