Skip to content

Commit

Permalink
add shards - RMSE - MAE experiment
Browse files Browse the repository at this point in the history
  • Loading branch information
fa1c4 committed Jan 3, 2022
1 parent 20c0140 commit 95cbf45
Show file tree
Hide file tree
Showing 79 changed files with 656,348 additions and 6,856 deletions.
37 changes: 7 additions & 30 deletions EDA/splitdata/spliting.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"metadata": {
"collapsed": true
},
Expand All @@ -14,19 +14,10 @@
},
{
"cell_type": "code",
"execution_count": 3,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"----- The folder exists! -----\n",
"../../data/shards_5_shuffled\n"
]
}
],
"execution_count": null,
"outputs": [],
"source": [
"shards = 5\n",
"shards = 16\n",
"shuffle = True\n",
"shuflled_ordered_str = 'shuffled' if shuffle else 'ordered'\n",
"\n",
Expand Down Expand Up @@ -54,7 +45,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"outputs": [],
"source": [
"def split(dataset_file, shards=5):\n",
Expand Down Expand Up @@ -86,22 +77,8 @@
},
{
"cell_type": "code",
"execution_count": 5,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"92732\n",
"../../data/shards_5_shuffled/dataset_sharded0.csv\n",
"../../data/shards_5_shuffled/dataset_sharded1.csv\n",
"../../data/shards_5_shuffled/dataset_sharded2.csv\n",
"../../data/shards_5_shuffled/dataset_sharded3.csv\n",
"../../data/shards_5_shuffled/dataset_sharded4.csv\n",
"----- done data spliting -----\n"
]
}
],
"execution_count": null,
"outputs": [],
"source": [
"if __name__ == \"__main__\":\n",
" dataset_file = open('../../data/train_data_{}.csv'.format(shuflled_ordered_str), \"rb\")\n",
Expand Down
Loading

0 comments on commit 95cbf45

Please sign in to comment.