fix error in data processing tutorials notebooks

DeepRank · Feb 19, 2024 · 43fb72d · 43fb72d
1 parent 6ab611d
commit 43fb72d
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 22 deletions.
diff --git a/tutorials/data_generation_ppi.ipynb b/tutorials/data_generation_ppi.ipynb
@@ -255,9 +255,7 @@
     "    grid_map_method=grid_map_method,\n",
     ")\n",
     "\n",
-    "print(\n",
-    "    f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"residue\")}.'\n",
-    ")"
+    "print(f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"residue\")}.')"
    ]
   },
   {
@@ -341,7 +339,7 @@
    "outputs": [],
    "source": [
     "processed_data = glob.glob(os.path.join(processed_data_path, \"residue\", \"*.hdf5\"))\n",
-    "dataset = GraphDataset(processed_data)\n",
+    "dataset = GraphDataset(processed_data, target=\"binary\")\n",
     "df = dataset.hdf5_to_pandas()\n",
     "df.head()"
    ]
@@ -360,9 +358,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "fname = os.path.join(\n",
-    "    processed_data_path, \"residue\", \"_\".join([\"res_mass\", \"distance\", \"electrostatic\"])\n",
-    ")\n",
+    "fname = os.path.join(processed_data_path, \"residue\", \"_\".join([\"res_mass\", \"distance\", \"electrostatic\"]))\n",
     "dataset.save_hist(features=[\"res_mass\", \"distance\", \"electrostatic\"], fname=fname)\n",
     "\n",
     "im = img.imread(fname + \".png\")\n",
@@ -480,9 +476,7 @@
     "    grid_map_method=grid_map_method,\n",
     ")\n",
     "\n",
-    "print(\n",
-    "    f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"atomic\")}.'\n",
-    ")"
+    "print(f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"atomic\")}.')"
    ]
   },
   {
@@ -500,7 +494,7 @@
    "outputs": [],
    "source": [
     "processed_data = glob.glob(os.path.join(processed_data_path, \"atomic\", \"*.hdf5\"))\n",
-    "dataset = GraphDataset(processed_data)\n",
+    "dataset = GraphDataset(processed_data, target=\"binary\")\n",
     "df = dataset.hdf5_to_pandas()\n",
     "df.head()"
    ]

diff --git a/tutorials/data_generation_srv.ipynb b/tutorials/data_generation_srv.ipynb
@@ -266,9 +266,7 @@
     "    grid_map_method=grid_map_method,\n",
     ")\n",
     "\n",
-    "print(\n",
-    "    f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"residue\")}.'\n",
-    ")"
+    "print(f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"residue\")}.')"
    ]
   },
   {
@@ -359,7 +357,7 @@
    "outputs": [],
    "source": [
     "processed_data = glob.glob(os.path.join(processed_data_path, \"residue\", \"*.hdf5\"))\n",
-    "dataset = GraphDataset(processed_data)\n",
+    "dataset = GraphDataset(processed_data, target=\"binary\")\n",
     "df = dataset.hdf5_to_pandas()\n",
     "df.head()"
    ]
@@ -378,9 +376,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "fname = os.path.join(\n",
-    "    processed_data_path, \"residue\", \"_\".join([\"res_mass\", \"distance\", \"electrostatic\"])\n",
-    ")\n",
+    "fname = os.path.join(processed_data_path, \"residue\", \"_\".join([\"res_mass\", \"distance\", \"electrostatic\"]))\n",
     "dataset.save_hist(features=[\"res_mass\", \"distance\", \"electrostatic\"], fname=fname)\n",
     "\n",
     "im = img.imread(fname + \".png\")\n",
@@ -500,9 +496,7 @@
     "    grid_map_method=grid_map_method,\n",
     ")\n",
     "\n",
-    "print(\n",
-    "    f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"atomic\")}.'\n",
-    ")"
+    "print(f'The queries processing is done. The generated HDF5 files are in {os.path.join(processed_data_path, \"atomic\")}.')"
    ]
   },
   {
@@ -520,7 +514,7 @@
    "outputs": [],
    "source": [
     "processed_data = glob.glob(os.path.join(processed_data_path, \"atomic\", \"*.hdf5\"))\n",
-    "dataset = GraphDataset(processed_data)\n",
+    "dataset = GraphDataset(processed_data, target=\"binary\")\n",
     "df = dataset.hdf5_to_pandas()\n",
     "df.head()"
    ]
@@ -548,6 +542,11 @@
    "source": [
     "Note that some of the features are different from the ones generated with the residue-level queries. There are indeed features in `deeprank2.features.components` module which are generated only in atomic graphs, i.e. `atom_type`, `atom_charge`, and `pdb_occupancy`, because they don't make sense only in the atomic graphs' representation.\n"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
   }
  ],
  "metadata": {