Skip to content

Fixed the plot.ipynb so that best prediction file per group could be … #13

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fixed the plot.ipynb so that best prediction file per group could be … #13

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6bea515
Fixed the plot.ipynb so that best prediction file per group could be …
Mar 22, 2024
0211c7e
Merge branch 'main' of github.com:RashikaRamola/CAFA-evaluator into main
May 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
56 changes: 24 additions & 32 deletions src/plot.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,18 +44,16 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Map column names to full names (for axis labels)\n",
"axis_title_dict = {'pr': 'Precision', 'rc': 'Recall', 'f': 'F-score', 'pr_w': 'Weighted Precision', 'rc_w': 'Weighted Recall', 'f_w': 'Weighted F-score', 'mi': 'Misinformation (Unweighted)', 'ru': 'Remaining Uncertainty (Unweighted)', 'mi_w': 'Misinformation', 'ru_w': 'Remaining Uncertainty', 's': 'S-score', 'pr_micro': 'Precision (Micro)', 'rc_micro': 'Recall (Micro)', 'f_micro': 'F-score (Micro)', 'pr_micro_w': 'Weighted Precision (Micro)', 'rc_micro_w': 'Weighted Recall (Micro)', 'f_micro_w': 'Weighted F-score (Micro)'}\n",
"\n",
"# Map ontology namespaces to full names (for plot titles)\n",
"ontology_dict = {'biological_process': 'BPO', 'molecular_function': 'MFO', 'cellular_component': 'CCO'}"
],
"metadata": {
"collapsed": false
},
"execution_count": null
]
},
{
"cell_type": "code",
Expand Down Expand Up @@ -88,7 +86,7 @@
" else:\n",
" df['is_baseline'].fillna(False, inplace=True)\n",
" # print(methods)\n",
"df = df.drop(columns='filename').set_index(['group', 'label', 'ns', 'tau'])\n",
"df = df.set_index(['group', 'label', 'ns', 'filename','tau'])\n",
"df"
]
},
Expand All @@ -105,6 +103,8 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Assign colors based on group\n",
Expand All @@ -113,9 +113,7 @@
"df['colors'] = pd.factorize(df['colors'])[0]\n",
"df['colors'] = df['colors'].apply(lambda x: cmap.colors[x % len(cmap.colors)])\n",
"df"
],
"metadata": {},
"execution_count": null
]
},
{
"cell_type": "code",
Expand Down Expand Up @@ -152,6 +150,8 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Add first last points to precision and recall curves to improve APS calculation\n",
Expand All @@ -165,47 +165,41 @@
"if metric.startswith('f') and add_extreme_points:\n",
" df_methods = df_methods.reset_index().groupby(['group', 'label', 'ns'], as_index=False).apply(add_points).set_index(['group', 'label', 'ns'])\n",
"df_methods"
],
"metadata": {
"collapsed": false
},
"execution_count": null
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Filter the dataframe for the best method and threshold\n",
"df_best = df.loc[index_best, ['cov', 'colors'] + cols + [metric]]\n",
"df_best"
],
"metadata": {},
"execution_count": null
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Calculate average precision score \n",
"if metric.startswith('f'):\n",
" df_best['aps'] = df_methods.groupby(level=['group', 'label', 'ns'])[[cols[0], cols[1]]].apply(lambda x: (x[cols[0]].diff(-1).shift(1) * x[cols[1]]).sum())\n",
"df_best"
],
"metadata": {
"collapsed": false
},
"execution_count": null
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Calculate the max coverage across all thresholds\n",
"df_best['max_cov'] = df_methods.groupby(level=['group', 'label', 'ns'])['cov'].max()\n",
"df_best"
],
"metadata": {},
"execution_count": null
]
},
{
"cell_type": "code",
Expand Down Expand Up @@ -247,7 +241,7 @@
"\n",
" # Iterate methods\n",
" for i, (index, row) in enumerate(df_g.sort_values(by=[metric, 'max_cov'], ascending=[False if metric.startswith('f') else True, False]).iterrows()):\n",
" data = df_methods.loc[index[:-1]]\n",
" data = df_methods.loc[index[:-2]]\n",
" \n",
" # Precision-recall or mi-ru curves\n",
" ax.plot(data[cols[0]], data[cols[1]], color=row['colors'], label=row['label'], lw=2, zorder=500-i)\n",
Expand Down Expand Up @@ -282,12 +276,10 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
},
"execution_count": null
"source": []
}
],
"metadata": {
Expand All @@ -306,7 +298,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.5"
"version": "3.10.9"
}
},
"nbformat": 4,
Expand Down