Add some metadata calculations

.gitignore

 # ignore venv
 stylo_venv/
 fanfic_venv/
-mic_venv/
\ No newline at end of file
+mic_venv/
+working_venv/
+venv/
\ No newline at end of file

cluster_files/submit_cluster_jobs/metadata.sh

+#!/bin/bash
+#
+#SBATCH --job-name=metadata
+#SBATCH --output=metadata.out
+#SBATCH --time=20:00
+#SBATCH --mem=64000mb
+#SBATCH --nodes=1
+#SBATCH --ntasks-per-node=1
+#SBATCH --partition=single
+#SBATCH --mail-user=chrysanthopoulou@cl.uni-heidelberg.de
+#SBATCH --mail-type=ALL
+
+python3 code/acquire_metadata.py
\ No newline at end of file

code/acquire_metadata.py

+from general_funcs_for_stylo import stylo_funcs
+import os
+
+universes = ['call_me_by_your_name', 'cosmere', 'divergent', 'grishaverse', 'maze_runner', 'murderbot', 'percy', 'red_white_royal_blue', 'school_for_good_and_evil', 'simonverse', 'song_of_achilles', 'throne_of_glass',]
+#universes = ['call_me_by_your_name']
+canon_tokens = {}
+for universe in universes:
+    texts = os.listdir(f"universes/{universe}/data/canon_works")
+    num_tokens_texts = 0
+    for text in texts:
+        with open(f"universes/{universe}/data/canon_works/{text}", "r", encoding='utf-8') as f:
+            text = f.read()
+        clean_tokens = stylo_funcs.tokenize_and_clean_text(text)
+        num_tokens_texts += len(clean_tokens)
+    canon_tokens[universe] = num_tokens_texts
+with open("canon_tokens.txt", "w", encoding='utf-8') as f:
+    f.write(str(canon_tokens))
\ No newline at end of file

metadata.out

+[nltk_data] Downloading package punkt to
+[nltk_data]     /home/hd/hd_hd/hd_vm255/nltk_data...
+[nltk_data]   Package punkt is already up-to-date!
+[nltk_data] Downloading package averaged_perceptron_tagger to
+[nltk_data]     /home/hd/hd_hd/hd_vm255/nltk_data...
+[nltk_data]   Package averaged_perceptron_tagger is already up-to-
+[nltk_data]       date!
+
+============================= JOB FEEDBACK =============================
+
+NodeName=uc2n405
+Job ID: 25088837
+Cluster: uc2
+User/Group: hd_vm255/hd_hd
+State: COMPLETED (exit code 0)
+Nodes: 1
+Cores per node: 2
+CPU Utilized: 00:01:41
+CPU Efficiency: 34.35% of 00:04:54 core-walltime
+Job Wall-clock time: 00:02:27
+Memory Utilized: 153.11 MB
+Memory Efficiency: 0.24% of 62.50 GB