20k train data

run.ipynb

@@ -132,7 +132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "3bc8418b-64f1-4163-a0ec-8e3293032341",
    "metadata": {},
    "outputs": [],
@@ -152,10 +152,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "id": "a18aea56-7fa1-40bd-8aa3-bbaf9d66d6b7",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "[NbConvertApp] Converting notebook run.ipynb to script\n",
+      "[NbConvertApp] Writing 1608 bytes to run.py\n"
+     ]
+    }
+   ],
    "source": [
     "!jupyter nbconvert --to script run.ipynb"
    ]

run.py

@@ -19,7 +19,7 @@ from sklearn.pipeline import make_pipeline
 
 train = pd.read_csv('train/train.tsv', header=None, sep='\t', error_bad_lines=False)
 print(len(train))
-train = train.head(20000)
+train = train.head(100000)
 
 
 # In[3]:
@@ -39,14 +39,14 @@ x_dev[20000] = "a ten tekst jest najbardziej testowy"
 y_dev = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t')
 
 
-# In[5]:
+# In[ ]:
 
 
 model = make_pipeline(TfidfVectorizer(), LinearRegression())
 model.fit(x_train, y_train)
 
 
-# In[6]:
+# In[ ]:
 
 
 dev_predicted =  model.predict(x_dev)
@@ -59,7 +59,7 @@ dev_out = pd.read_csv('dev-0/out.tsv', header=None, sep='\t')
 dev_expected = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t')
 
 
-# In[7]:
+# In[ ]:
 
 
 print(mean_squared_error(dev_out, dev_expected))