remove row limits from data
This commit is contained in:
parent
2af8e67c62
commit
3dc4b5a074
28
bayess.ipynb
28
bayess.ipynb
@ -3,7 +3,6 @@
|
|||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 1,
|
"execution_count": 1,
|
||||||
"id": "5fcb7312",
|
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -19,7 +18,6 @@
|
|||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 2,
|
"execution_count": 2,
|
||||||
"id": "88ac1be8",
|
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -28,14 +26,22 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 14,
|
"execution_count": 3,
|
||||||
"id": "4aa43416",
|
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stderr",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"/home/ubuntu/anaconda3/lib/python3.8/site-packages/sklearn/utils/validation.py:73: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
|
||||||
|
" return f(**kwargs)\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
"source": [
|
"source": [
|
||||||
"#training\n",
|
"#training\n",
|
||||||
"all_train_data_in = pd.read_csv('train/in.tsv.xz', compression='xz', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t', nrows=3000)\n",
|
"all_train_data_in = pd.read_csv('train/in.tsv.xz', compression='xz', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t')\n",
|
||||||
"train_data_ex = pd.read_csv('train/expected.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t', nrows=3000)\n",
|
"train_data_ex = pd.read_csv('train/expected.tsv', header=None, error_bad_lines=False, quoting=csv.QUOTE_NONE, sep='\\t')\n",
|
||||||
"train_data_in = []\n",
|
"train_data_in = []\n",
|
||||||
"for value in all_train_data_in.values:\n",
|
"for value in all_train_data_in.values:\n",
|
||||||
" temp = \"\"\n",
|
" temp = \"\"\n",
|
||||||
@ -51,8 +57,7 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 17,
|
"execution_count": 4,
|
||||||
"id": "15c47c24",
|
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -77,8 +82,7 @@
|
|||||||
},
|
},
|
||||||
{
|
{
|
||||||
"cell_type": "code",
|
"cell_type": "code",
|
||||||
"execution_count": 16,
|
"execution_count": 5,
|
||||||
"id": "822b1e29",
|
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"outputs": [],
|
"outputs": [],
|
||||||
"source": [
|
"source": [
|
||||||
@ -118,7 +122,7 @@
|
|||||||
"name": "python",
|
"name": "python",
|
||||||
"nbconvert_exporter": "python",
|
"nbconvert_exporter": "python",
|
||||||
"pygments_lexer": "ipython3",
|
"pygments_lexer": "ipython3",
|
||||||
"version": "3.8.8"
|
"version": "3.8.3"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"nbformat": 4,
|
"nbformat": 4,
|
||||||
|
1130
dev-0/out.tsv
1130
dev-0/out.tsv
File diff suppressed because it is too large
Load Diff
1208
test-A/out.tsv
1208
test-A/out.tsv
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue
Block a user