solution + out files

script.py

@@ -0,0 +1,68 @@
+
+man = ['silnik', 'windows', 'silnika', 'gb', 'mb', 'meczu', 'pc', 'opony', 'apple', 'iphone', 'zwiastuny', 'hd',
+       'ubuntu', 'systemu', 'serwer']
+woman = ['ciąży', 'miesiączki', 'ciasto', 'ciążę', 'zadowolona', 'ciąża', 'ciazy', 'antykoncepcyjne', 'ginekologa',
+         'tabletki', 'porodzie', 'mąż', 'miesiączkę', 'krwawienie', 'ciasta']
+
+
+# stemowanie
+def steming(man, woman):
+    man_stem = []
+    woman_stem = []
+    for i in man:
+        man_stem.append(i[:5].lower())
+    for i in woman:
+        woman_stem.append(i[:5].lower())
+    return man_stem, woman_stem
+
+
+def predict(man_stem, woman_stem, dane):
+    res = []
+    i = 0
+    for s in dane:
+        man_count = 0
+        woman_count = 0
+        t = s.split()
+
+        for w in t:
+            if w[:5].lower() in man_stem:
+                man_count += 1
+            elif w[:5].lower() in woman_stem:
+                woman_count += 1
+        if man_count >= woman_count:
+            res.append('1')
+        elif man_count < woman_count:
+            res.append('0')
+    return res
+
+
+def out_file(res, name):
+    with open(name, 'w') as file:
+        for p in res:
+            file.write(p + "\n")
+
+
+man_dict, woman_dict = steming(man, woman)
+dane = []
+with open('dev-0/in.tsv') as data:
+    for idx, line in enumerate(data.readlines()):
+        dane.append(line.replace('\n', ''))
+
+result = predict(man_dict, woman_dict, dane)
+out_file(result, 'dev-0/out.tsv')
+
+dane2 = []
+with open('dev-1/in.tsv') as data:
+    for idx, line in enumerate(data.readlines()):
+        dane2.append(line.replace('\n', ''))
+
+result = predict(man_dict, woman_dict, dane2)
+out_file(result, 'dev-1/out.tsv')
+
+dane3 = []
+with open('test-A/in.tsv') as data:
+    for idx, line in enumerate(data.readlines()):
+        dane3.append(line.replace('\n', ''))
+
+result = predict(man_dict, woman_dict, dane3)
+out_file(result, 'test-A/out.tsv')