51% .py

dev-0/model.ipynb

@@ -3,7 +3,7 @@
   {
    "cell_type": "code",
    "execution_count": 90,
-   "id": "5b55a105",
+   "id": "7dc5e391",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -14,7 +14,7 @@
   {
    "cell_type": "code",
    "execution_count": 91,
-   "id": "9364cf2c",
+   "id": "a0825c64",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -24,7 +24,7 @@
   {
    "cell_type": "code",
    "execution_count": 139,
-   "id": "9d3f7db9",
+   "id": "4b9092a6",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -34,7 +34,7 @@
   {
    "cell_type": "code",
    "execution_count": 94,
-   "id": "5062478d",
+   "id": "56c39aa1",
    "metadata": {},
    "outputs": [
     {
@@ -54,7 +54,7 @@
   {
    "cell_type": "code",
    "execution_count": 158,
-   "id": "5eca7aab",
+   "id": "d7b300ca",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -67,7 +67,7 @@
   {
    "cell_type": "code",
    "execution_count": 159,
-   "id": "0bdd1845",
+   "id": "31b5864b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -82,7 +82,7 @@
   {
    "cell_type": "code",
    "execution_count": 160,
-   "id": "b36bbd92",
+   "id": "c1f02d77",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -94,7 +94,7 @@
   {
    "cell_type": "code",
    "execution_count": 161,
-   "id": "ccbad95c",
+   "id": "6edfd944",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -109,7 +109,7 @@
   {
    "cell_type": "code",
    "execution_count": 162,
-   "id": "02ee0acf",
+   "id": "40369c2b",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -124,7 +124,7 @@
   {
    "cell_type": "code",
    "execution_count": 163,
-   "id": "db803a58",
+   "id": "e296921c",
    "metadata": {},
    "outputs": [
     {
@@ -141,87 +141,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 164,
-   "id": "e1a15db7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "['cierpi',\n",
-       " 'na',\n",
-       " 'strasz',\n",
-       " 'lagi',\n",
-       " '–',\n",
-       " 'kilkan',\n",
-       " 'sekund',\n",
-       " 'lub',\n",
-       " 'dłużej',\n",
-       " 'czarne',\n",
-       " 'ekranu',\n",
-       " 'przy',\n",
-       " 'próbie',\n",
-       " 'przełą',\n",
-       " 'się',\n",
-       " '/',\n",
-       " 'urucho',\n",
-       " 'prawie',\n",
-       " 'każdej',\n",
-       " 'aplika',\n",
-       " 'dodatk',\n",
-       " 'telefo',\n",
-       " 'mi',\n",
-       " 'się',\n",
-       " 'wyłącz',\n",
-       " 'czasem',\n",
-       " 'bez',\n",
-       " 'powodu',\n",
-       " '–',\n",
-       " 'sam',\n",
-       " 'z',\n",
-       " 'siebie',\n",
-       " 'albo',\n",
-       " 'reseto',\n",
-       " 'ostatn',\n",
-       " 'nawet',\n",
-       " 'przegl',\n",
-       " 'zaczęł',\n",
-       " 'się',\n",
-       " 'często',\n",
-       " 'zawies',\n",
-       " 'i',\n",
-       " 'androi',\n",
-       " 'propon',\n",
-       " 'wymusz',\n",
-       " 'zamkni',\n",
-       " 'do',\n",
-       " 'tego',\n",
-       " 'te',\n",
-       " 'proble',\n",
-       " 'z',\n",
-       " 'połącz',\n",
-       " 'do',\n",
-       " 'komput',\n",
-       " 'przez',\n",
-       " 'usb.']"
-      ]
-     },
-     "execution_count": 164,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "trimmed_docs[0]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7403c1bb",
+   "execution_count": 167,
+   "id": "fee431a4",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "df = pd.DataFrame(result)\n",
+    "df.to_csv('out.tsv', sep = '\\t')"
+   ]
   }
  ],
  "metadata": {

dev-0/model.py

@@ -0,0 +1,91 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[90]:
+
+
+import pandas as pd
+import csv
+
+
+# In[91]:
+
+
+tsv_data = pd.read_csv('in.tsv', sep='\t',header=None, quoting=csv.QUOTE_NONE)[0]
+
+
+# In[139]:
+
+
+expected = pd.read_csv('expected.tsv', sep='\t',header=None)[0]
+
+
+# In[94]:
+
+
+print(len(expected))
+print(len(tsv_data))
+
+
+# In[158]:
+
+
+male={'silnik', 'windows', 'gb', 'mb', 'mecz', 'pc', 'opony', 'apple', 'iphone', 'zwiastuny', 'hd', 'ubuntu', 'system', 'serwer'}
+female={'ciąża', 'miesiączki', 'ciasto', 'ciąże', 'zadowolona', 'antykoncepcyjne', 'ginekologia', 'tabletki', 'porodzie', 'mąż', 'krwawienie', 'ciasta'}
+male = {x[:6].lower() for x in male}
+female = {x[:6].lower() for x in female}
+
+
+# In[159]:
+
+
+trimmed_docs=[]
+for document in tsv_data:
+    new_doc=[]
+    for word in str(document).lower().split():
+        new_doc.append(word[:6])
+    trimmed_docs.append(new_doc)
+
+
+# In[160]:
+
+
+male_or_female=[]
+for doc in trimmed_docs:
+    male_or_female.append((len(male&set(doc)), len(female&set(doc))))
+
+
+# In[161]:
+
+
+answers=[]
+for i in male_or_female:
+    if i[0]>i[1]:
+        answers.append(1)
+    else:
+        answers.append(0)
+
+
+# In[162]:
+
+
+result=[]
+for i in range(len(answers)):
+    if answers[i]==expected[i]:
+        result.append(1)
+    else:
+        result.append(0)
+
+
+# In[163]:
+
+
+print(f'Predykcja modelu wynosi {sum(result)/len(result)*100:.6f}%')
+
+
+# In[167]:
+
+
+df = pd.DataFrame(result)
+df.to_csv('out.tsv', sep = '\t')
+