selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2025-12-21 04:39:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

organize imports

Browse Source
This commit is contained in:
Gokul Mohanarangan
2023-07-25 10:02:25 +05:30
parent ab42858ec8
commit 25f34bf9e5
8 changed files with 79 additions and 80 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
utils/viz_utilities.py
View File

@@ -13,7 +13,7 @@ from wordcloud import STOPWORDS, WordCloud
en = spacy.load('en_core_web_md')
spacy_stopwords = en.Defaults.stop_words
STOPWORDS = set(STOPWORDS).union(set(stopwords.words("english"))).\
STOPWORDS = set(STOPWORDS).union(set(stopwords.words("english"))). \
union(set(spacy_stopwords))
@@ -24,7 +24,7 @@ def create_wordcloud(timestamp, real_time=False):
"""
filename = "transcript"
if real_time:
filename = "real_time_" + filename + "_" +\
filename = "real_time_" + filename + "_" + \
timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
else:
filename += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
@@ -47,7 +47,7 @@ def create_wordcloud(timestamp, real_time=False):
wordcloud_name = "wordcloud"
if real_time:
wordcloud_name = "real_time_" + wordcloud_name + "_" +\
wordcloud_name = "real_time_" + wordcloud_name + "_" + \
timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".png"
else:
wordcloud_name += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".png"
@@ -57,12 +57,12 @@ def create_wordcloud(timestamp, real_time=False):
def create_talk_diff_scatter_viz(timestamp, real_time=False):
"""
Perform agenda vs transription diff to see covered topics.
Perform agenda vs transcription diff to see covered topics.
Create a scatter plot of words in topics.
:return: None. Saved locally.
"""
spaCy_model = "en_core_web_md"
nlp = spacy.load(spaCy_model)
spacy_model = "en_core_web_md"
nlp = spacy.load(spacy_model)
nlp.add_pipe('sentencizer')
agenda_topics = []
@@ -75,12 +75,11 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
agenda_topics.append(line.split(":")[0])
# Load the transcription with timestamp
filename = ""
if real_time:
filename = "./artefacts/real_time_transcript_with_timestamp_" +\
filename = "./artefacts/real_time_transcript_with_timestamp_" + \
timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
else:
filename = "./artefacts/transcript_with_timestamp_" +\
filename = "./artefacts/transcript_with_timestamp_" + \
timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".txt"
with open(filename) as f:
transcription_timestamp_text = f.read()
@@ -142,7 +141,7 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
df = df.apply(create_new_columns, axis=1)
# Count the number of items covered and calculatre the percentage
# Count the number of items covered and calculate the percentage
num_covered_items = sum(covered_items.values())
percentage_covered = num_covered_items / len(agenda) * 100
@@ -158,7 +157,7 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
# Save df, mappings for further experimentation
df_name = "df"
if real_time:
df_name = "real_time_" + df_name + "_" +\
df_name = "real_time_" + df_name + "_" + \
timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"
else:
df_name += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"
@@ -169,7 +168,7 @@ def create_talk_diff_scatter_viz(timestamp, real_time=False):
mappings_name = "mappings"
if real_time:
mappings_name = "real_time_" + mappings_name + "_" +\
mappings_name = "real_time_" + mappings_name + "_" + \
timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"
else:
mappings_name += "_" + timestamp.strftime("%m-%d-%Y_%H:%M:%S") + ".pkl"