stellargraph/stellargraph

View on GitHub
demos/node-classification/graphsage-node-classification.ipynb

Summary

Maintainability
Test Coverage
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "0",
   "metadata": {},
   "source": [
    "# Node classification with GraphSAGE"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1",
   "metadata": {
    "nbsphinx": "hidden",
    "tags": [
     "CloudRunner"
    ]
   },
   "source": [
    "<table><tr><td>Run the latest release of this notebook:</td><td><a href=\"https://mybinder.org/v2/gh/stellargraph/stellargraph/master?urlpath=lab/tree/demos/node-classification/graphsage-node-classification.ipynb\" alt=\"Open In Binder\" target=\"_parent\"><img src=\"https://mybinder.org/badge_logo.svg\"/></a></td><td><a href=\"https://colab.research.google.com/github/stellargraph/stellargraph/blob/master/demos/node-classification/graphsage-node-classification.ipynb\" alt=\"Open In Colab\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\"/></a></td></tr></table>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2",
   "metadata": {},
   "source": [
    "Import stellargraph:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "3",
   "metadata": {
    "nbsphinx": "hidden",
    "tags": [
     "CloudRunner"
    ]
   },
   "outputs": [],
   "source": [
    "# install StellarGraph if running on Google Colab\n",
    "import sys\n",
    "if 'google.colab' in sys.modules:\n",
    "  %pip install -q stellargraph[demos]==1.3.0b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "4",
   "metadata": {
    "nbsphinx": "hidden",
    "tags": [
     "VersionCheck"
    ]
   },
   "outputs": [],
   "source": [
    "# verify that we're using the correct version of StellarGraph for this notebook\n",
    "import stellargraph as sg\n",
    "\n",
    "try:\n",
    "    sg.utils.validate_notebook_version(\"1.3.0b\")\n",
    "except AttributeError:\n",
    "    raise ValueError(\n",
    "        f\"This notebook requires StellarGraph version 1.3.0b, but a different version {sg.__version__} is installed.  Please see <https://github.com/stellargraph/stellargraph/issues/1172>.\"\n",
    "    ) from None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import networkx as nx\n",
    "import pandas as pd\n",
    "import os\n",
    "\n",
    "import stellargraph as sg\n",
    "from stellargraph.mapper import GraphSAGENodeGenerator\n",
    "from stellargraph.layer import GraphSAGE\n",
    "\n",
    "from tensorflow.keras import layers, optimizers, losses, metrics, Model\n",
    "from sklearn import preprocessing, feature_extraction, model_selection\n",
    "from stellargraph import datasets\n",
    "from IPython.display import display, HTML\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6",
   "metadata": {},
   "source": [
    "## Loading the CORA network"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7",
   "metadata": {
    "tags": [
     "DataLoadingLinks"
    ]
   },
   "source": [
    "(See [the \"Loading from Pandas\" demo](../basics/loading-pandas.ipynb) for details on how data can be loaded.)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8",
   "metadata": {
    "tags": [
     "DataLoading"
    ]
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "The Cora dataset consists of 2708 scientific publications classified into one of seven classes. The citation network consists of 5429 links. Each publication in the dataset is described by a 0/1-valued word vector indicating the absence/presence of the corresponding word from the dictionary. The dictionary consists of 1433 unique words."
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset = datasets.Cora()\n",
    "display(HTML(dataset.description))\n",
    "G, node_subjects = dataset.load()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "StellarGraph: Undirected multigraph\n",
      " Nodes: 2708, Edges: 5429\n",
      "\n",
      " Node types:\n",
      "  paper: [2708]\n",
      "    Edge types: paper-cites->paper\n",
      "\n",
      " Edge types:\n",
      "    paper-cites->paper: [5429]\n"
     ]
    }
   ],
   "source": [
    "print(G.info())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "10",
   "metadata": {},
   "source": [
    "We aim to train a graph-ML model that will predict the \"subject\" attribute on the nodes. These subjects are one of 7 categories:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "11",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Case_Based',\n",
       " 'Genetic_Algorithms',\n",
       " 'Neural_Networks',\n",
       " 'Probabilistic_Methods',\n",
       " 'Reinforcement_Learning',\n",
       " 'Rule_Learning',\n",
       " 'Theory'}"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "set(node_subjects)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "12",
   "metadata": {},
   "source": [
    "### Splitting the data"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13",
   "metadata": {},
   "source": [
    "For machine learning we want to take a subset of the nodes for training, and use the rest for testing. We'll use scikit-learn again to do this"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "14",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_subjects, test_subjects = model_selection.train_test_split(\n",
    "    node_subjects, train_size=0.1, test_size=None, stratify=node_subjects\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15",
   "metadata": {},
   "source": [
    "Note using stratified sampling gives the following counts:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "16",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Counter({'Probabilistic_Methods': 42,\n",
       "         'Genetic_Algorithms': 42,\n",
       "         'Reinforcement_Learning': 22,\n",
       "         'Rule_Learning': 18,\n",
       "         'Neural_Networks': 81,\n",
       "         'Case_Based': 30,\n",
       "         'Theory': 35})"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from collections import Counter\n",
    "\n",
    "Counter(train_subjects)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "17",
   "metadata": {},
   "source": [
    "The training set has class imbalance that might need to be compensated, e.g., via using a weighted cross-entropy loss in model training, with class weights inversely proportional to class support. However, we will ignore the class imbalance in this example, for simplicity."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "18",
   "metadata": {},
   "source": [
    "### Converting to numeric arrays"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "19",
   "metadata": {},
   "source": [
    "For our categorical target, we will use one-hot vectors that will be fed into a soft-max Keras layer during training. To do this conversion ..."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "20",
   "metadata": {},
   "outputs": [],
   "source": [
    "target_encoding = preprocessing.LabelBinarizer()\n",
    "\n",
    "train_targets = target_encoding.fit_transform(train_subjects)\n",
    "test_targets = target_encoding.transform(test_subjects)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "21",
   "metadata": {},
   "source": [
    "We now do the same for the node attributes we want to use to predict the subject. These are the feature vectors that the Keras model will use as input. The CORA dataset contains attributes 'w_x' that correspond to words found in that publication. If a word occurs more than once in a publication the relevant attribute will be set to one, otherwise it will be zero."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "22",
   "metadata": {},
   "source": [
    "## Creating the GraphSAGE model in Keras"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23",
   "metadata": {},
   "source": [
    "To feed data from the graph to the Keras model we need a data generator that feeds data from the graph to the model. The generators are specialized to the model and the learning task so we choose the `GraphSAGENodeGenerator` as we are predicting node attributes with a GraphSAGE model.\n",
    "\n",
    "We need two other parameters, the `batch_size` to use for training and the number of nodes to sample at each level of the model. Here we choose a two-level model with 10 nodes sampled in the first layer, and 5 in the second."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "24",
   "metadata": {},
   "outputs": [],
   "source": [
    "batch_size = 50\n",
    "num_samples = [10, 5]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "25",
   "metadata": {},
   "source": [
    "A `GraphSAGENodeGenerator` object is required to send the node features in sampled subgraphs to Keras"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "26",
   "metadata": {},
   "outputs": [],
   "source": [
    "generator = GraphSAGENodeGenerator(G, batch_size, num_samples)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "27",
   "metadata": {},
   "source": [
    "Using the `generator.flow()` method, we can create iterators over nodes that should be used to train, validate, or evaluate the model. For training we use only the training nodes returned from our splitter and the target values. The `shuffle=True` argument is given to the `flow` method to improve training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "28",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_gen = generator.flow(train_subjects.index, train_targets, shuffle=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "29",
   "metadata": {},
   "source": [
    "Now we can specify our machine learning model, we need a few more parameters for this:\n",
    "\n",
    " * the `layer_sizes` is a list of hidden feature sizes of each layer in the model. In this example we use 32-dimensional hidden node features at each layer.\n",
    " * The `bias` and `dropout` are internal parameters of the model. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "30",
   "metadata": {},
   "outputs": [],
   "source": [
    "graphsage_model = GraphSAGE(\n",
    "    layer_sizes=[32, 32], generator=generator, bias=True, dropout=0.5,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "31",
   "metadata": {},
   "source": [
    "Now we create a model to predict the 7 categories using Keras softmax layers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "32",
   "metadata": {},
   "outputs": [],
   "source": [
    "x_inp, x_out = graphsage_model.in_out_tensors()\n",
    "prediction = layers.Dense(units=train_targets.shape[1], activation=\"softmax\")(x_out)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33",
   "metadata": {},
   "source": [
    "### Training the model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "34",
   "metadata": {},
   "source": [
    "Now let's create the actual Keras model with the graph inputs `x_inp` provided by the `graph_model` and outputs being the predictions from the softmax layer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "35",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = Model(inputs=x_inp, outputs=prediction)\n",
    "model.compile(\n",
    "    optimizer=optimizers.Adam(lr=0.005),\n",
    "    loss=losses.categorical_crossentropy,\n",
    "    metrics=[\"acc\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36",
   "metadata": {},
   "source": [
    "Train the model, keeping track of its loss and accuracy on the training set, and its generalisation performance on the test set (we need to create another generator over the test data for this)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "37",
   "metadata": {},
   "outputs": [],
   "source": [
    "test_gen = generator.flow(test_subjects.index, test_targets)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "38",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/20\n",
      "6/6 - 2s - loss: 1.8488 - acc: 0.3037 - val_loss: 1.6904 - val_acc: 0.3794\n",
      "Epoch 2/20\n",
      "6/6 - 2s - loss: 1.6272 - acc: 0.4852 - val_loss: 1.5230 - val_acc: 0.5349\n",
      "Epoch 3/20\n",
      "6/6 - 2s - loss: 1.4474 - acc: 0.6333 - val_loss: 1.3641 - val_acc: 0.6829\n",
      "Epoch 4/20\n",
      "6/6 - 2s - loss: 1.2771 - acc: 0.7630 - val_loss: 1.2483 - val_acc: 0.7186\n",
      "Epoch 5/20\n",
      "6/6 - 2s - loss: 1.1698 - acc: 0.8444 - val_loss: 1.1501 - val_acc: 0.7498\n",
      "Epoch 6/20\n",
      "6/6 - 2s - loss: 1.0364 - acc: 0.9000 - val_loss: 1.0619 - val_acc: 0.7756\n",
      "Epoch 7/20\n",
      "6/6 - 2s - loss: 0.9260 - acc: 0.8963 - val_loss: 0.9960 - val_acc: 0.7896\n",
      "Epoch 8/20\n",
      "6/6 - 2s - loss: 0.8232 - acc: 0.9000 - val_loss: 0.9372 - val_acc: 0.7986\n",
      "Epoch 9/20\n",
      "6/6 - 2s - loss: 0.7396 - acc: 0.9481 - val_loss: 0.8897 - val_acc: 0.8056\n",
      "Epoch 10/20\n",
      "6/6 - 2s - loss: 0.6708 - acc: 0.9630 - val_loss: 0.8496 - val_acc: 0.8056\n",
      "Epoch 11/20\n",
      "6/6 - 2s - loss: 0.5816 - acc: 0.9667 - val_loss: 0.8084 - val_acc: 0.8162\n",
      "Epoch 12/20\n",
      "6/6 - 2s - loss: 0.5232 - acc: 0.9852 - val_loss: 0.7748 - val_acc: 0.8175\n",
      "Epoch 13/20\n",
      "6/6 - 2s - loss: 0.4801 - acc: 0.9778 - val_loss: 0.7515 - val_acc: 0.8154\n",
      "Epoch 14/20\n",
      "6/6 - 2s - loss: 0.4383 - acc: 0.9852 - val_loss: 0.7452 - val_acc: 0.8097\n",
      "Epoch 15/20\n",
      "6/6 - 2s - loss: 0.4116 - acc: 0.9778 - val_loss: 0.7161 - val_acc: 0.8187\n",
      "Epoch 16/20\n",
      "6/6 - 2s - loss: 0.3584 - acc: 0.9889 - val_loss: 0.7039 - val_acc: 0.8187\n",
      "Epoch 17/20\n",
      "6/6 - 2s - loss: 0.3559 - acc: 0.9815 - val_loss: 0.6767 - val_acc: 0.8240\n",
      "Epoch 18/20\n",
      "6/6 - 2s - loss: 0.3104 - acc: 0.9889 - val_loss: 0.6849 - val_acc: 0.8146\n",
      "Epoch 19/20\n",
      "6/6 - 2s - loss: 0.2925 - acc: 0.9815 - val_loss: 0.6698 - val_acc: 0.8162\n",
      "Epoch 20/20\n",
      "6/6 - 2s - loss: 0.2690 - acc: 0.9852 - val_loss: 0.6559 - val_acc: 0.8199\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(\n",
    "    train_gen, epochs=20, validation_data=test_gen, verbose=2, shuffle=False\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "39",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x576 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "sg.utils.plot_history(history)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "40",
   "metadata": {},
   "source": [
    "Now we have trained the model we can evaluate on the test set."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "41",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Test Set Metrics:\n",
      "\tloss: 0.6601\n",
      "\tacc: 0.8228\n"
     ]
    }
   ],
   "source": [
    "test_metrics = model.evaluate(test_gen)\n",
    "print(\"\\nTest Set Metrics:\")\n",
    "for name, val in zip(model.metrics_names, test_metrics):\n",
    "    print(\"\\t{}: {:0.4f}\".format(name, val))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42",
   "metadata": {},
   "source": [
    "### Making predictions with the model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "43",
   "metadata": {},
   "source": [
    "Now let's get the predictions themselves for all nodes using another node iterator:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "44",
   "metadata": {},
   "outputs": [],
   "source": [
    "all_nodes = node_subjects.index\n",
    "all_mapper = generator.flow(all_nodes)\n",
    "all_predictions = model.predict(all_mapper)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "45",
   "metadata": {},
   "source": [
    "These predictions will be the output of the softmax layer, so to get final categories we'll use the `inverse_transform` method of our target attribute specification to turn these values back to the original categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "46",
   "metadata": {},
   "outputs": [],
   "source": [
    "node_predictions = target_encoding.inverse_transform(all_predictions)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "47",
   "metadata": {},
   "source": [
    "Let's have a look at a few:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "48",
   "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>Predicted</th>\n",
       "      <th>True</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>31336</td>\n",
       "      <td>Neural_Networks</td>\n",
       "      <td>Neural_Networks</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1061127</td>\n",
       "      <td>Rule_Learning</td>\n",
       "      <td>Rule_Learning</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1106406</td>\n",
       "      <td>Reinforcement_Learning</td>\n",
       "      <td>Reinforcement_Learning</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>13195</td>\n",
       "      <td>Reinforcement_Learning</td>\n",
       "      <td>Reinforcement_Learning</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>37879</td>\n",
       "      <td>Probabilistic_Methods</td>\n",
       "      <td>Probabilistic_Methods</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1126012</td>\n",
       "      <td>Reinforcement_Learning</td>\n",
       "      <td>Probabilistic_Methods</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1107140</td>\n",
       "      <td>Reinforcement_Learning</td>\n",
       "      <td>Theory</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1102850</td>\n",
       "      <td>Neural_Networks</td>\n",
       "      <td>Neural_Networks</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>31349</td>\n",
       "      <td>Neural_Networks</td>\n",
       "      <td>Neural_Networks</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>1106418</td>\n",
       "      <td>Theory</td>\n",
       "      <td>Theory</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      Predicted                    True\n",
       "31336           Neural_Networks         Neural_Networks\n",
       "1061127           Rule_Learning           Rule_Learning\n",
       "1106406  Reinforcement_Learning  Reinforcement_Learning\n",
       "13195    Reinforcement_Learning  Reinforcement_Learning\n",
       "37879     Probabilistic_Methods   Probabilistic_Methods\n",
       "1126012  Reinforcement_Learning   Probabilistic_Methods\n",
       "1107140  Reinforcement_Learning                  Theory\n",
       "1102850         Neural_Networks         Neural_Networks\n",
       "31349           Neural_Networks         Neural_Networks\n",
       "1106418                  Theory                  Theory"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\"Predicted\": node_predictions, \"True\": node_subjects})\n",
    "df.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "49",
   "metadata": {},
   "source": [
    "Create a NetworkX graph to save it as GraphML, e.g. for visualisation in [Gephi](https://gephi.org). This adds the predictions to the graph before saving too."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "50",
   "metadata": {},
   "outputs": [],
   "source": [
    "Gnx = G.to_networkx(feature_attr=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "51",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nid, pred, true in zip(df.index, df[\"Predicted\"], df[\"True\"]):\n",
    "    Gnx.nodes[nid][\"subject\"] = true\n",
    "    Gnx.nodes[nid][\"PREDICTED_subject\"] = pred.split(\"=\")[-1]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "52",
   "metadata": {},
   "source": [
    "Also add `isTrain` and `isCorrect` node attributes:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "53",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nid in train_subjects.index:\n",
    "    Gnx.nodes[nid][\"isTrain\"] = True\n",
    "\n",
    "for nid in test_subjects.index:\n",
    "    Gnx.nodes[nid][\"isTrain\"] = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "54",
   "metadata": {},
   "outputs": [],
   "source": [
    "for nid in Gnx.nodes():\n",
    "    Gnx.nodes[nid][\"isCorrect\"] = (\n",
    "        Gnx.nodes[nid][\"subject\"] == Gnx.nodes[nid][\"PREDICTED_subject\"]\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "55",
   "metadata": {},
   "source": [
    "Save in GraphML format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "56",
   "metadata": {},
   "outputs": [],
   "source": [
    "pred_fname = \"pred_n={}.graphml\".format(num_samples)\n",
    "nx.write_graphml(Gnx, os.path.join(dataset.data_directory, pred_fname))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "57",
   "metadata": {},
   "source": [
    "## Node embeddings\n",
    "Evaluate node embeddings as activations of the output of GraphSAGE layer stack, and visualise them, coloring nodes by their subject label.\n",
    "\n",
    "The GraphSAGE embeddings are the output of the GraphSAGE layers, namely the `x_out` variable. Let's create a new model with the same inputs as we used previously `x_inp` but now the output is the embeddings rather than the predicted class. Additionally note that the weights trained previously are kept in the new model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "58",
   "metadata": {},
   "outputs": [],
   "source": [
    "embedding_model = Model(inputs=x_inp, outputs=x_out)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "59",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2708, 32)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emb = embedding_model.predict(all_mapper)\n",
    "emb.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "60",
   "metadata": {},
   "source": [
    "Project the embeddings to 2d using either TSNE or PCA transform, and visualise, coloring nodes by their subject label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "61",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.decomposition import PCA\n",
    "from sklearn.manifold import TSNE\n",
    "import pandas as pd\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "62",
   "metadata": {},
   "outputs": [],
   "source": [
    "X = emb\n",
    "y = np.argmax(target_encoding.transform(node_subjects), axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "63",
   "metadata": {},
   "outputs": [],
   "source": [
    "if X.shape[1] > 2:\n",
    "    transform = TSNE  # PCA\n",
    "\n",
    "    trans = transform(n_components=2)\n",
    "    emb_transformed = pd.DataFrame(trans.fit_transform(X), index=node_subjects.index)\n",
    "    emb_transformed[\"label\"] = y\n",
    "else:\n",
    "    emb_transformed = pd.DataFrame(X, index=node_subjects.index)\n",
    "    emb_transformed = emb_transformed.rename(columns={\"0\": 0, \"1\": 1})\n",
    "    emb_transformed[\"label\"] = y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "64",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 504x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "alpha = 0.7\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(7, 7))\n",
    "ax.scatter(\n",
    "    emb_transformed[0],\n",
    "    emb_transformed[1],\n",
    "    c=emb_transformed[\"label\"].astype(\"category\"),\n",
    "    cmap=\"jet\",\n",
    "    alpha=alpha,\n",
    ")\n",
    "ax.set(aspect=\"equal\", xlabel=\"$X_1$\", ylabel=\"$X_2$\")\n",
    "plt.title(\n",
    "    \"{} visualization of GraphSAGE embeddings for cora dataset\".format(transform.__name__)\n",
    ")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65",
   "metadata": {
    "nbsphinx": "hidden",
    "tags": [
     "CloudRunner"
    ]
   },
   "source": [
    "<table><tr><td>Run the latest release of this notebook:</td><td><a href=\"https://mybinder.org/v2/gh/stellargraph/stellargraph/master?urlpath=lab/tree/demos/node-classification/graphsage-node-classification.ipynb\" alt=\"Open In Binder\" target=\"_parent\"><img src=\"https://mybinder.org/badge_logo.svg\"/></a></td><td><a href=\"https://colab.research.google.com/github/stellargraph/stellargraph/blob/master/demos/node-classification/graphsage-node-classification.ipynb\" alt=\"Open In Colab\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\"/></a></td></tr></table>"
   ]
  }
 ],
 "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": "3.6.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}