Add run.py and remove train directory

CHANGELOG.md

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

README.md

@@ -1,38 +0,0 @@
-
-"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

@@ -1 +0,0 @@
---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 +1,37 @@
+import random
+
+
+women_word_list = ["mąż", "fryzjer", "kosmety", "biżuter", "sukienk", "polk", "kolczy", "rodzin", "obcas",
+                   "bransolet", "spink", "torebk", "szmink", "kobiet", "koleżan", "kuchni", "gotowa", "przepis",
+                   "ciast", "ciąż", "miesiączk"]
+men_word_list = ["samoch", "kompute", "pc", "sport", "km", "windows", "paliw", "kierownic", "silnik", "opon", "piw",
+                 "koleg", "śrub", "mecz", "system", "serwer"]
+
+data = []
+with open("j:\Desktop\ekstrakcjacw5\petite-difference-challenge2\\test-A\in.tsv", "r", encoding="UTF-8") as read_file:
+    counter = 0
+    for line in read_file.readlines():
+        is_written = False
+        counter += 1
+        for word in men_word_list:
+            if word in line:
+                data.append("1\n")
+                is_written = True
+                break
+
+        if is_written is True:
+            continue
+
+        for word in women_word_list:
+            if word in line:
+                data.append("0\n")
+                is_written = True
+                break
+
+        if is_written is True:
+            continue
+        else:
+            data.append(f"{(random.randint(0, 1))}\n")
+
+with open("j:\Desktop\ekstrakcjacw5\petite-difference-challenge2\\test-A\out.tsv", "w", encoding="UTF-8") as output_file:
+    output_file.writelines(data)