4

.ipynb_checkpoints/run-checkpoint.ipynb

@@ -44,7 +44,7 @@
    "source": [
     "train = pd.read_csv('train/train.tsv', header=None, sep='\\t', error_bad_lines=False)\n",
     "print(len(train))\n",
-    "train = train.head(40000)"
+    "train = train.head(10000)"
    ]
   },
   {
@@ -122,7 +122,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "4289.2810262872745\n"
+      "4086.3369441409172\n"
      ]
     }
    ],

run.ipynb

@@ -44,7 +44,7 @@
    "source": [
     "train = pd.read_csv('train/train.tsv', header=None, sep='\\t', error_bad_lines=False)\n",
     "print(len(train))\n",
-    "train = train.head(40000)"
+    "train = train.head(10000)"
    ]
   },
   {
@@ -122,7 +122,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "4289.2810262872745\n"
+      "4086.3369441409172\n"
      ]
     }
    ],

run.py

@@ -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[ ]:
+# In[5]:
 
 
 model = make_pipeline(TfidfVectorizer(), LinearRegression())
 model.fit(x_train, y_train)
 
 
-# In[ ]:
+# In[6]:
 
 
 dev_predicted =  model.predict(x_dev)
@@ -59,13 +59,13 @@ 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[ ]:
+# In[7]:
 
 
 print(mean_squared_error(dev_out, dev_expected))
 
 
-# In[ ]:
+# In[8]:
 
 
 with open('test-A/in.tsv', 'r', encoding = 'utf-8') as f:
@@ -81,7 +81,7 @@ with open('test-A/out.tsv', 'wt') as f:
         f.write(str(i)+'\n')
 
 
-# In[ ]:
+# In[9]:
 
 
 get_ipython().system('jupyter nbconvert --to script run.ipynb')