From f5226bf91b3ae2e9354d825512b1505abb957173 Mon Sep 17 00:00:00 2001
From: chrysanthopoulou <chrysanthopoulou@cl.uni-heidelberg.de>
Date: Wed, 12 Apr 2023 23:47:49 +0200
Subject: [PATCH] Fix some trailing lines
---
stylometry_code.py | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/stylometry_code.py b/stylometry_code.py
index 16fdcaf..061eb54 100644
--- a/stylometry_code.py
+++ b/stylometry_code.py
@@ -74,10 +74,8 @@ def standardised_type_token_ratio(tokens):
types = set(tokens)
std_ttr = len(types)/len(tokens)
print("Warning: Text was too short for segmentation!")
- print(ttrs)
else:
std_ttr = statistics.mean(ttrs)
- print(ttrs)
return std_ttr
@@ -151,19 +149,11 @@ def mendenhall_curve(corpus, curve_title, plot_destination):
standard_deviation = statistics.stdev(token_lengths)
mean = statistics.mean(token_lengths)
- # to get the number of unique tokens, i.e., types, I'm converting
- # my list to a set (and back). I could also transform it to a pandas
- # series, and drop the duplicates, but: if it is stupid and it works
- # it isn't stupid
-
- types_set = set(short_clean_tokens)
- #type_token_ratio = len(types_set)/len(short_clean_tokens)
type_token_ratio = standardised_type_token_ratio(short_clean_tokens)
return standard_deviation, mean, type_token_ratio
-
#create the Mendenhall Curve for the Throne of Glass Series
std_dev_tokens_tog_canon, mean_tokens_tog_canon, type_token_ratio_tog_canon = mendenhall_curve(read_works_into_string(f"throne_of_glass/data/canon_works"), "Mendenhall Curve for the Throne of Glass Series", f"throne_of_glass/freq_distribution/all_canon_token_len.png")
--
GitLab