Datasets
Models
Downloads: 1
428 lines (427 with data), 13.7 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"metadata": {}
},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"metadata": {}
},
"outputs": [],
"source": [
"# df = pd.read_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/ovarian_semi_synthetic_rf.csv\", index_col=0)\n",
"#df = pd.read_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/ovarian_semi_synthetic_l1.csv\", index_col=0)\n",
"df = pd.read_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/melanoma_semi_synthetic_l1.csv\", index_col=0)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"metadata": {}
},
"outputs": [],
"source": [
"df_gt = df.iloc[:,:2]\n",
"df_data = df.iloc[:,2:]"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"metadata": {}
},
"outputs": [],
"source": [
"df_data.iloc[:,:2] = (df_data.iloc[:,:2] > 0.5).astype(int)"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {
"metadata": {}
},
"outputs": [
{
"data": {
"text/plain": [
"0.1989795918367347"
]
},
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(df_data.iloc[:,0]>df_data.iloc[:,1]).mean()"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {
"metadata": {}
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>immuno</th>\n",
" <th>titodeath_geq4</th>\n",
" <th>pred_a0_y2 (immuno)</th>\n",
" <th>pred_a1_y2 (immuno)</th>\n",
" <th>TuPro</th>\n",
" <th>treline</th>\n",
" <th>age</th>\n",
" <th>charlci</th>\n",
" <th>clinstage</th>\n",
" <th>pradiot</th>\n",
" <th>pio</th>\n",
" <th>psyst</th>\n",
" <th>ecog</th>\n",
" <th>brainmets</th>\n",
" </tr>\n",
" <tr>\n",
" <th>ID</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>vajun-jinok</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.589392</td>\n",
" <td>0.552390</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>50.0</td>\n",
" <td>6.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>pifop-balap</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.364219</td>\n",
" <td>0.448789</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>67.0</td>\n",
" <td>8.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mijud-dator</th>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0.659857</td>\n",
" <td>0.453112</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>53.0</td>\n",
" <td>7.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fobus-fudor</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.209008</td>\n",
" <td>0.357861</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>70.0</td>\n",
" <td>9.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>2.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>tabom-supum</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.832661</td>\n",
" <td>0.700153</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>68.0</td>\n",
" <td>8.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fizol-botad</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.283023</td>\n",
" <td>0.234100</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>75.0</td>\n",
" <td>9.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>fofiz-tuvak</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.374240</td>\n",
" <td>0.286329</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>41.0</td>\n",
" <td>6.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>foniz-rijoj</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.427237</td>\n",
" <td>0.235907</td>\n",
" <td>1.0</td>\n",
" <td>3.0</td>\n",
" <td>58.0</td>\n",
" <td>7.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>nugiz-bilin</th>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.684217</td>\n",
" <td>0.686841</td>\n",
" <td>0.0</td>\n",
" <td>2.0</td>\n",
" <td>60.0</td>\n",
" <td>8.0</td>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>bamip-lumak</th>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.825362</td>\n",
" <td>0.366591</td>\n",
" <td>1.0</td>\n",
" <td>4.0</td>\n",
" <td>69.0</td>\n",
" <td>8.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>196 rows × 14 columns</p>\n",
"</div>"
],
"text/plain": [
" immuno titodeath_geq4 pred_a0_y2 (immuno) pred_a1_y2 (immuno) \\\n",
"ID \n",
"vajun-jinok 1 0 0.589392 0.552390 \n",
"pifop-balap 1 0 0.364219 0.448789 \n",
"mijud-dator 1 1 0.659857 0.453112 \n",
"fobus-fudor 1 0 0.209008 0.357861 \n",
"tabom-supum 1 0 0.832661 0.700153 \n",
"... ... ... ... ... \n",
"fizol-botad 0 0 0.283023 0.234100 \n",
"fofiz-tuvak 0 0 0.374240 0.286329 \n",
"foniz-rijoj 0 0 0.427237 0.235907 \n",
"nugiz-bilin 0 1 0.684217 0.686841 \n",
"bamip-lumak 0 0 0.825362 0.366591 \n",
"\n",
" TuPro treline age charlci clinstage pradiot pio psyst \\\n",
"ID \n",
"vajun-jinok 1.0 2.0 50.0 6.0 4.0 1.0 1.0 0.0 \n",
"pifop-balap 0.0 1.0 67.0 8.0 4.0 0.0 0.0 0.0 \n",
"mijud-dator 0.0 1.0 53.0 7.0 4.0 0.0 1.0 0.0 \n",
"fobus-fudor 1.0 3.0 70.0 9.0 4.0 0.0 1.0 1.0 \n",
"tabom-supum 0.0 1.0 68.0 8.0 4.0 1.0 0.0 0.0 \n",
"... ... ... ... ... ... ... ... ... \n",
"fizol-botad 0.0 2.0 75.0 9.0 4.0 0.0 1.0 0.0 \n",
"fofiz-tuvak 0.0 5.0 41.0 6.0 4.0 1.0 1.0 1.0 \n",
"foniz-rijoj 1.0 3.0 58.0 7.0 4.0 1.0 1.0 0.0 \n",
"nugiz-bilin 0.0 2.0 60.0 8.0 4.0 1.0 1.0 0.0 \n",
"bamip-lumak 1.0 4.0 69.0 8.0 4.0 0.0 1.0 1.0 \n",
"\n",
" ecog brainmets \n",
"ID \n",
"vajun-jinok 0.0 0.0 \n",
"pifop-balap 2.0 1.0 \n",
"mijud-dator 1.0 1.0 \n",
"fobus-fudor 2.0 0.0 \n",
"tabom-supum 0.0 1.0 \n",
"... ... ... \n",
"fizol-botad 1.0 0.0 \n",
"fofiz-tuvak 3.0 1.0 \n",
"foniz-rijoj 1.0 0.0 \n",
"nugiz-bilin 0.0 0.0 \n",
"bamip-lumak 0.0 0.0 \n",
"\n",
"[196 rows x 14 columns]"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {
"metadata": {}
},
"outputs": [],
"source": [
"# df_gt.to_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/ovarian_semi_synthetic_rf_groundtruth.csv\")\n",
"# df_gt.to_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/ovarian_semi_synthetic_l1_groundtruth.csv\")\n",
"df_gt.to_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/melanoma_semi_synthetic_l1_groundtruth.csv\")\n",
"\n",
"# df_data.to_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/ovarian_semi_synthetic_rf.csv\")\n",
"# df_data.to_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/ovarian_semi_synthetic_l1.csv\")\n",
"df_data.to_csv(\"/cluster/work/tumorp/analysis/wickilab/data/DepMap_24Q2/real/melanoma_semi_synthetic_l1.csv\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv_tumorp",
"language": "python",
"name": ".venv_tumorp"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
}
},
"nbformat": 4,
"nbformat_minor": 2
}