478873

.gitignore

@@ -0,0 +1 @@
+*~

CHANGELOG.md

@@ -0,0 +1,4 @@
+<a name="2.0.0"></a>
+## 2.0.0 (2020-05-22)
+
+* Switch to probabilities as the main metric

README.md

@@ -0,0 +1,38 @@
+
+"He Said She Said" classification challenge (2nd edition)
+=========================================================
+
+Give the probability that a text in Polish was written by a man.
+
+This challenge is based on the "He Said She Said" corpus for Polish.
+The corpus was created by grepping gender-specific first person
+expressions (e.g. "zrobiłem/zrobiłam", "jestem zadowolony/zadowolona",
+"będę robił/robiła") in the Common Crawl corpus. Such expressions were
+normalised here into masculine forms.
+
+Classes
+-------
+
+* `0` — text written by a woman
+* `1` — text written by a man
+
+Directory structure
+-------------------
+
+* `README.md` — this file
+* `config.txt` — configuration file
+* `train/` — directory with training data
+* `train/train.tsv.gz` — train set (gzipped), the class is given in the first column,
+  a text fragment in the second one
+* `train/meta.tsv.gz` — metadata (do not use during training)
+* `dev-0/` — directory with dev (test) data
+* `dev-0/in.tsv` — input data for the dev set (text fragments)
+* `dev-0/expected.tsv` — expected (reference) data for the dev set
+* `dev-0/meta.tsv` — metadata (not used during testing)
+* `dev-1/` — directory with extra dev (test) data
+* `dev-1/in.tsv` — input data for the extra dev set (text fragments)
+* `dev-1/expected.tsv` — expected (reference) data for the extra dev set
+* `dev-1/meta.tsv` — metadata (not used during testing)
+* `test-A` — directory with test data
+* `test-A/in.tsv` — input data for the test set (text fragments)
+* `test-A/expected.tsv` — expected (reference) data for the test set (hidden)

config.txt

@@ -0,0 +1 @@
+--metric Likelihood --metric Accuracy --metric {Likelihood:N<Likelihood>,Accuracy:N<Accuracy>}P<2>{f<in[2]:for-humans>N<+H>,f<in[3]:contaminated>N<+C>,f<in[3]:not-contaminated>N<-C>}  --precision 5

run.py

@@ -0,0 +1,52 @@
+from sklearn.metrics import recall_score
+from sklearn.metrics import precision_score
+from sklearn.metrics import accuracy_score
+from sklearn.metrics import f1_score
+
+male = ['windows', 'gb', 'mb', 'meczu', 'pc', 'opony', 'apple', 'iphone', 'zwiast', 'hd', 'ubunt', 
+        'system', 'serwer', "youtub", "sfd", "kfd", "elektr", "autoce", "dobrep",'merced', 'bmw',
+        'audi', 'porsch', 'gry', 'gra','gram' 'cs', 'counte', 'piłka', 'mecz', 'gol', 'bramka', 'linux',
+        'robota','felga','lagi' 'żona', 'żona', 'żony', 'żonie', 'żoną', 'zona', 'zony', 'zonie', 'komput', 'inform'
+        'sserwer', 'ziom', 'ziomków', 'ziomkow', 'kumpel', 'kolega', 'kolegą', 'kolegi', 'pad'
+        ]
+
+
+female = ['ciąży', 'miesią', 'ciasto', 'ciążę', 'zadowo', 'ciąża', 'ciazy', 'antyko', 'gineko',
+         'tablet', 'porodz', 'mąż', 'miesią', 'krwawi', 'ciasta', 'sukien', 'podpas', 'szmink',
+          'maz', 'męża', 'męza', 'mąż', 'chłopak', 'szpilk'
+     ]
+
+
+
+def prediction(male,female, in_file):
+    results = []
+    with open(in_file, encoding='utf-8',) as file:
+            for line in file.readlines():
+                text = line.split("\t")[0].strip()
+                text = text.replace(",","").replace(".","").replace("/","").replace("–","").replace(":","").lower()
+                stem_words = [word[:6] for word in text.split()]
+
+                man_score = len([w for w in stem_words if w in male])
+                girl_score = len([w for w in stem_words if w in female])
+                if man_score > girl_score:
+                    results.append('1')
+                else:
+                    results.append('0')
+    return results
+
+
+def out_file(result, out_file):
+    with open(out_file, 'w') as file:
+        for r in result:
+            file.write(r + "\n")
+            
+
+
+result = prediction(male,female,'dev-0/in.tsv')
+out_file(result, 'dev-0/out.tsv')
+
+result = prediction(male,female,'dev-1/in.tsv')
+out_file(result, 'dev-1/out.tsv')
+
+result = prediction(male,female,'test-A/in.tsv')
+out_file(result, 'test-A/out.tsv')