Skip to content

Instantly share code, notes, and snippets.

@Neeratyoy

Neeratyoy/Using OpenML 4.ipynb

Created October 25, 2019 16:15
Show Gist options
  • Save Neeratyoy/f694f1961a72649c8f4f1c26d4aeda9e to your computer and use it in GitHub Desktop.
Save Neeratyoy/f694f1961a72649c8f4f1c26d4aeda9e to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Using OpenML 4.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"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>tid</th>\n",
" <th>ttid</th>\n",
" <th>did</th>\n",
" <th>name</th>\n",
" <th>task_type</th>\n",
" <th>status</th>\n",
" <th>estimation_procedure</th>\n",
" <th>evaluation_measures</th>\n",
" <th>source_data</th>\n",
" <th>target_feature</th>\n",
" <th>...</th>\n",
" <th>NumberOfFeatures</th>\n",
" <th>NumberOfInstances</th>\n",
" <th>NumberOfInstancesWithMissingValues</th>\n",
" <th>NumberOfMissingValues</th>\n",
" <th>NumberOfNumericFeatures</th>\n",
" <th>NumberOfSymbolicFeatures</th>\n",
" <th>number_samples</th>\n",
" <th>cost_matrix</th>\n",
" <th>quality_measure</th>\n",
" <th>target_value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>59</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>10-fold Crossvalidation</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>118</th>\n",
" <td>118</td>\n",
" <td>3</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Learning Curve</td>\n",
" <td>active</td>\n",
" <td>10 times 10-fold Learning Curve</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>289</th>\n",
" <td>289</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>33% Holdout set</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1758</th>\n",
" <td>1758</td>\n",
" <td>3</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Learning Curve</td>\n",
" <td>active</td>\n",
" <td>10-fold Learning Curve</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1823</th>\n",
" <td>1823</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>5 times 2-fold Crossvalidation</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 24 columns</p>\n",
"</div>"
],
"text/plain": [
" tid ttid did name task_type status \\\n",
"59 59 1 61 iris Supervised Classification active \n",
"118 118 3 61 iris Learning Curve active \n",
"289 289 1 61 iris Supervised Classification active \n",
"1758 1758 3 61 iris Learning Curve active \n",
"1823 1823 1 61 iris Supervised Classification active \n",
"\n",
" estimation_procedure evaluation_measures source_data \\\n",
"59 10-fold Crossvalidation predictive_accuracy 61 \n",
"118 10 times 10-fold Learning Curve predictive_accuracy 61 \n",
"289 33% Holdout set predictive_accuracy 61 \n",
"1758 10-fold Learning Curve predictive_accuracy 61 \n",
"1823 5 times 2-fold Crossvalidation predictive_accuracy 61 \n",
"\n",
" target_feature ... NumberOfFeatures NumberOfInstances \\\n",
"59 class ... 5 150 \n",
"118 class ... 5 150 \n",
"289 class ... 5 150 \n",
"1758 class ... 5 150 \n",
"1823 class ... 5 150 \n",
"\n",
" NumberOfInstancesWithMissingValues NumberOfMissingValues \\\n",
"59 0 0 \n",
"118 0 0 \n",
"289 0 0 \n",
"1758 0 0 \n",
"1823 0 0 \n",
"\n",
" NumberOfNumericFeatures NumberOfSymbolicFeatures number_samples \\\n",
"59 4 1 NaN \n",
"118 4 1 4 \n",
"289 4 1 NaN \n",
"1758 4 1 4 \n",
"1823 4 1 NaN \n",
"\n",
" cost_matrix quality_measure target_value \n",
"59 NaN NaN NaN \n",
"118 NaN NaN NaN \n",
"289 NaN NaN NaN \n",
"1758 NaN NaN NaN \n",
"1823 NaN NaN NaN \n",
"\n",
"[5 rows x 24 columns]"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = openml.tasks.list_tasks(data_id=61, output_format='dataframe')\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 2,
"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>tid</th>\n",
" <th>ttid</th>\n",
" <th>did</th>\n",
" <th>name</th>\n",
" <th>task_type</th>\n",
" <th>status</th>\n",
" <th>estimation_procedure</th>\n",
" <th>evaluation_measures</th>\n",
" <th>source_data</th>\n",
" <th>target_feature</th>\n",
" <th>...</th>\n",
" <th>NumberOfFeatures</th>\n",
" <th>NumberOfInstances</th>\n",
" <th>NumberOfInstancesWithMissingValues</th>\n",
" <th>NumberOfMissingValues</th>\n",
" <th>NumberOfNumericFeatures</th>\n",
" <th>NumberOfSymbolicFeatures</th>\n",
" <th>number_samples</th>\n",
" <th>cost_matrix</th>\n",
" <th>quality_measure</th>\n",
" <th>target_value</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>59</th>\n",
" <td>59</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>10-fold Crossvalidation</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>289</th>\n",
" <td>289</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>33% Holdout set</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1823</th>\n",
" <td>1823</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>5 times 2-fold Crossvalidation</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1939</th>\n",
" <td>1939</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>10 times 10-fold Crossvalidation</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1992</th>\n",
" <td>1992</td>\n",
" <td>1</td>\n",
" <td>61</td>\n",
" <td>iris</td>\n",
" <td>Supervised Classification</td>\n",
" <td>active</td>\n",
" <td>Leave one out</td>\n",
" <td>predictive_accuracy</td>\n",
" <td>61</td>\n",
" <td>class</td>\n",
" <td>...</td>\n",
" <td>5</td>\n",
" <td>150</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 24 columns</p>\n",
"</div>"
],
"text/plain": [
" tid ttid did name task_type status \\\n",
"59 59 1 61 iris Supervised Classification active \n",
"289 289 1 61 iris Supervised Classification active \n",
"1823 1823 1 61 iris Supervised Classification active \n",
"1939 1939 1 61 iris Supervised Classification active \n",
"1992 1992 1 61 iris Supervised Classification active \n",
"\n",
" estimation_procedure evaluation_measures source_data \\\n",
"59 10-fold Crossvalidation predictive_accuracy 61 \n",
"289 33% Holdout set predictive_accuracy 61 \n",
"1823 5 times 2-fold Crossvalidation predictive_accuracy 61 \n",
"1939 10 times 10-fold Crossvalidation predictive_accuracy 61 \n",
"1992 Leave one out predictive_accuracy 61 \n",
"\n",
" target_feature ... NumberOfFeatures NumberOfInstances \\\n",
"59 class ... 5 150 \n",
"289 class ... 5 150 \n",
"1823 class ... 5 150 \n",
"1939 class ... 5 150 \n",
"1992 class ... 5 150 \n",
"\n",
" NumberOfInstancesWithMissingValues NumberOfMissingValues \\\n",
"59 0 0 \n",
"289 0 0 \n",
"1823 0 0 \n",
"1939 0 0 \n",
"1992 0 0 \n",
"\n",
" NumberOfNumericFeatures NumberOfSymbolicFeatures number_samples \\\n",
"59 4 1 NaN \n",
"289 4 1 NaN \n",
"1823 4 1 NaN \n",
"1939 4 1 NaN \n",
"1992 4 1 NaN \n",
"\n",
" cost_matrix quality_measure target_value \n",
"59 NaN NaN NaN \n",
"289 NaN NaN NaN \n",
"1823 NaN NaN NaN \n",
"1939 NaN NaN NaN \n",
"1992 NaN NaN NaN \n",
"\n",
"[5 rows x 24 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Filtering only the Supervised Classification tasks on Iris\n",
"df.query(\"task_type=='Supervised Classification'\").head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"11\n"
]
}
],
"source": [
"# Collecting all relevant task_ids\n",
"tasks = df.query(\"task_type=='Supervised Classification'\")['tid'].to_numpy()\n",
"print(len(tasks))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment