s478839/retroc2
1
0
Fork 0
forked from kubapok/retroc2
Code Issues Pull Requests Projects Releases Wiki Activity

20k train data

Browse Source
This commit is contained in:
Sebastian 2022-05-18 00:34:09 +02:00
parent 5a6487da37
commit f130909428
2 changed files with 16 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
run.ipynb
View File

@ -132,7 +132,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 8,
"id": "3bc8418b-64f1-4163-a0ec-8e3293032341", "id": "3bc8418b-64f1-4163-a0ec-8e3293032341",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -152,10 +152,19 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 9,
"id": "a18aea56-7fa1-40bd-8aa3-bbaf9d66d6b7", "id": "a18aea56-7fa1-40bd-8aa3-bbaf9d66d6b7",
"metadata": {}, "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": [ "source": [
"!jupyter nbconvert --to script run.ipynb" "!jupyter nbconvert --to script run.ipynb"
] ]

8
run.py
View File

@ -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) train = pd.read_csv('train/train.tsv', header=None, sep='\t', error_bad_lines=False)
print(len(train)) print(len(train))
train = train.head(20000) train = train.head(100000)
# In[3]: # 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') y_dev = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t')
# In[5]: # In[ ]:
model = make_pipeline(TfidfVectorizer(), LinearRegression()) model = make_pipeline(TfidfVectorizer(), LinearRegression())
model.fit(x_train, y_train) model.fit(x_train, y_train)
# In[6]: # In[ ]:
dev_predicted = model.predict(x_dev) 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') dev_expected = pd.read_csv('dev-0/expected.tsv', header=None, sep='\t')
# In[7]: # In[ ]:
print(mean_squared_error(dev_out, dev_expected)) print(mean_squared_error(dev_out, dev_expected))