s443930

.ipynb_checkpoints/inout-checkpoint.py

@@ -0,0 +1,25 @@
+import csv, lzma
+
+# Reads input from directory and returns a list
+def read(dir):
+    X = []
+    if 'xz' in dir:
+        with lzma.open(dir) as f:
+            for line in f:
+                text = line.decode('utf-8')
+                text = text.replace('\n', '').split('\t')
+                X.append(text)
+    else:
+        with open(dir, encoding='utf-8') as f:
+            for line in f:
+                if 'tsv' in dir:
+                    X.append(line.replace('\n', '').split('\t'))
+                else:
+                    X.append(line.replace('\n', ''))
+    return X
+
+# Takes the output (list) and writes it into directory
+def write(output, dir):
+    with open(dir, 'w', newline='', encoding='utf-8') as f:
+        writer = csv.writer(f)
+        for row in output: writer.writerow([row])

decode.py

@@ -13,6 +13,7 @@ if __name__ == '__main__':
     files = ['dev-0', 'test-A', 'test-B']
 
     for file in files:
-        predicted = io.read(file)
+        predicted = io.read('predicted-' + file)
-        predicted = [categories[round(float(x))] for x in predicted]
+        predicted = [1 if float(x)-1 <= -0.5 else x for x in predicted]
+        predicted = [categories[round(float(x))-1] for x in predicted]
         io.write(predicted, file + '/out.tsv')

main.sh

@@ -0,0 +1,6 @@
+python3 rockyRoadtoDublin.py
+vw vw-train -f vw.model
+vw -i vw.model -t vw-dev0 -p predicted-dev-0 --quiet
+vw -i vw.model -t vw-test-A -p predicted-test-A --quiet
+vw -i vw.model -t vw-test-B -p predicted-test-B --quiet
+python3 decode.py