Field-Aware Factorization Machines

field_aware_factorization_machine.ipynb

{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import torch\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\nimport torch.nn as nn\n\nfrom scipy.stats import rankdata\nfrom sklearn.preprocessing import LabelEncoder","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:23.762107Z","iopub.execute_input":"2022-10-31T06:43:23.762926Z","iopub.status.idle":"2022-10-31T06:43:26.757470Z","shell.execute_reply.started":"2022-10-31T06:43:23.762803Z","shell.execute_reply":"2022-10-31T06:43:26.756389Z"},"trusted":true},"execution_count":1,"outputs":[]},{"cell_type":"code","source":"device = 'cuda' if torch.cuda.is_available() else 'cpu'\nPAD_IDX = 0","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:26.762024Z","iopub.execute_input":"2022-10-31T06:43:26.763192Z","iopub.status.idle":"2022-10-31T06:43:26.838995Z","shell.execute_reply.started":"2022-10-31T06:43:26.763147Z","shell.execute_reply":"2022-10-31T06:43:26.837958Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"# purpose: convert target with index of movie to series of all zeros and one in place of index\n# We will use this to compute the expected output of the model to be compared with actual output\ndef idx_to_sparse(idx, sparse_dim):\n    sparse = np.zeros(sparse_dim) # vector of 1683 zeroes\n    sparse[int(idx)] = 1 # set a given index to 1\n    return pd.Series(sparse, dtype=int) # make a pandas series of 0s and 1s\n\n\n# Calculate accuracy (a classification metric)\ndef accuracy_fn(y_true, y_pred):\n    correct = torch.eq(y_true, y_pred).sum().item() # torch.eq() calculates where two tensors are equal\n    acc = (correct / len(y_pred)) * 100 \n    return acc","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:26.843519Z","iopub.execute_input":"2022-10-31T06:43:26.844496Z","iopub.status.idle":"2022-10-31T06:43:26.855128Z","shell.execute_reply.started":"2022-10-31T06:43:26.844457Z","shell.execute_reply":"2022-10-31T06:43:26.853894Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"def load_and_process_data_ffm():\n    #Load the Ratings data\n    data = pd.read_csv('../input/movielens-100k-dataset/ml-100k/u.data', sep=\"\\t\", header=None)\n    data.columns = ['user id', 'movie id', 'rating', 'timestamp']\n    #Load the User data\n    users = pd.read_csv('../input/movielens-100k-dataset/ml-100k/u.user', sep=\"|\", encoding='latin-1', header=None)\n    users.columns = ['user id', 'age', 'gender', 'occupation', 'zip code']\n    #Load movie data\n    items = pd.read_csv('../input/movielens-100k-dataset/ml-100k/u.item', \n                    sep=\"|\", encoding='latin-1', header=None)\n    items.columns = ['movie id', 'movie title' ,'release date','video release date', 'IMDb URL', \n                     'unknown', 'Action', 'Adventure', 'Animation', 'Children\\'s', 'Comedy', \n                     'Crime', 'Documentary', 'Drama', 'Fantasy', 'Film-Noir', 'Horror', \n                     'Musical', 'Mystery', 'Romance', 'Sci-Fi', 'Thriller', 'War', 'Western']\n    GENRES = pd.read_csv('../input/movielens-100k-dataset/ml-100k/u.genre', \n                     sep=\"|\", header=None, usecols=[0])[0].tolist()\n    \n    # Sort the dataset by user-id and time\n    dataset = data.sort_values(['user id', 'timestamp']).reset_index(drop=True)\n    dataset['one'] = 1 # add a column containing all 1s\n    dataset['sample_num'] = dataset.groupby('user id')['one'].cumsum() # use the 1s column to create a sample number for each user\n    # Create a target column by shifting movie-id for each user-id one step back, effectively this means that we have a column that has id for the next movie the user is going to watch \n    # (it is NaN for the row representing the last movie the user watches). We will predict this column.\n    dataset['target'] = dataset.groupby('user id')['movie id'].shift(-1)\n    # create a column that represents average movie rating given by user till that time (represented by row)\n    dataset['mean_rate'] = dataset.groupby('user id')['rating'].cumsum() / dataset['sample_num']\n    \n    # do a left join with movies dataframe and bring all the genre representations (0/1 binary values for each movie representing its category) here.\n    dataset = dataset.merge(items[['movie id'] + GENRES], on='movie id', how='left')\n    \n    # For each genre column (19) creates another column (total 19 more). This column represents a given user's mean score (float value) for a given genre till that time (represented by row).\n    # Note that we also update the genre columns such that each column now has cumulative sum, i.e. the corresponding number of movies that the user has watched in that genre so far.\n    for genre in GENRES:\n        dataset[f'{genre}_rate'] = dataset[genre]*dataset['rating']\n        dataset[genre] = dataset.groupby('user id')[genre].cumsum()\n        dataset[f'{genre}_rate'] = dataset.groupby('user id')[f'{genre}_rate'].cumsum() / dataset[genre]\n    \n    # Next we normalize the scores for movies in each genre such that we divide it by the number of movies that the user has watched so far.\n    dataset[GENRES] = dataset[GENRES].apply(lambda x: x / dataset['sample_num'])\n    # do a left-join on users data and get more information on users\n    dataset = dataset.merge(users, on='user id', how='left')\n    \n    gender_encoder = LabelEncoder()\n    occupations_encoder = LabelEncoder()\n    dataset['gender'] = gender_encoder.fit_transform(dataset['gender'])\n    dataset['occupation'] = occupations_encoder.fit_transform(dataset['occupation'])\n    \n    dataset.drop('zip code', axis=1, inplace=True)\n    \n    COLD_START_TRESH = 5 # take the rows AFTER each user has watched at least 4 movies\n    # filter using threshold and remove null target rows\n    filtred_data = dataset[(dataset['sample_num'] >= COLD_START_TRESH) &\n                           ~(dataset['target'].isna())].sort_values('timestamp')\n    \n    continuous_cols = ['age', 'mean_rate'] + GENRES + [gen+\"_rate\" for gen in GENRES] # 41\n    categoricals = ['gender', 'occupation'] # label encoded\n    field_dims = []\n    field_dims.append(len(gender_encoder.classes_))\n    field_dims.append(len(occupations_encoder.classes_))\n    df_continuous = filtred_data[continuous_cols]\n    df_categorical = filtred_data[categoricals]\n    \n    TEST_SIZE = 0.2 # size of test set\n    X_train_continuous, X_test_continuous = df_continuous[:int(len(df_continuous)*(1-TEST_SIZE))], df_continuous[int(len(df_continuous)*(1-TEST_SIZE)):]\n    X_train_categorical, X_test_categorical = df_categorical[:int(len(df_categorical)*(1-TEST_SIZE))], df_categorical[int(len(df_categorical)*(1-TEST_SIZE)):]\n\n    filtered_train_data, filtered_test_data = filtred_data[:int(len(filtred_data)*(1-TEST_SIZE))], filtred_data[int(len(filtred_data)*(1-TEST_SIZE)):]\n    y_train, y_test = filtered_train_data['target'], filtered_test_data['target']\n    \n    # target\n    target_train = torch.Tensor(y_train.values).long().to(device)\n    target_test = torch.Tensor(y_test.values).long().to(device)\n    target_test_sparse = y_test.apply(lambda x: idx_to_sparse(x, items['movie id'].nunique() + 1)) # to calculate mean rank over test set during training\n    \n    # tensor with continuous features\n    X_train_continuous_tensor = torch.Tensor(X_train_continuous.fillna(0).values).to(device)\n    X_test_continuous_tensor = torch.Tensor(X_test_continuous.fillna(0).values).to(device)\n    X_train_categorical_tensor = torch.Tensor(X_train_categorical.fillna(0).values).to(device)\n    X_test_categorical_tensor = torch.Tensor(X_test_categorical.fillna(0).values).to(device)\n    \n    return X_train_continuous_tensor, X_test_continuous_tensor, X_train_categorical_tensor, X_test_categorical_tensor,  target_train, target_test, target_test_sparse, field_dims, items['movie id'].nunique() + 1\n\nclass FFM(nn.Module):\n    def __init__(self, continuous_dim, field_dims, n_class, embed_dim=16, pad_idx=0):\n        super().__init__()\n        self.bias = nn.Parameter(torch.zeros((n_class,)))\n        self.embeddings = nn.Embedding(sum(field_dims), n_class, padding_idx=pad_idx, device=device)\n        \n        self.num_fields = len(field_dims)\n        self.embeddings_interaction = nn.ModuleList([\n            nn.Embedding(sum(field_dims), embed_dim, padding_idx=pad_idx, device=device) for _ in range(self.num_fields)\n        ])\n        \n        self.linear_layer = nn.Linear(continuous_dim, n_class, device=device)\n\n    def forward(self, continuous_X, categorical_X):\n        embeds_out = torch.sum(self.embeddings(categorical_X), dim=1) + self.bias.to(device)\n        \n        field_wise_emb_list = [self.embeddings_interaction[i](categorical_X) for i in range(self.num_fields)]\n        ix = list()\n        for i in range(self.num_fields - 1):\n            for j in range(i + 1, self.num_fields):\n                ix.append(field_wise_emb_list[j][:, i] * field_wise_emb_list[i][:, j])\n        ix = torch.stack(ix, dim=1)\n        ffm_interaction_term = torch.sum(torch.sum(ix, dim=1), dim=1, keepdim=True)\n        output = self.linear_layer(continuous_X) + embeds_out + ffm_interaction_term\n        return output\n\ndef run_gradient_descent_ffm(model,\n    learning_rate=1e-3,\n    weight_decay=0.01,\n    num_epochs=10):\n    loss_fn = nn.CrossEntropyLoss(ignore_index=PAD_IDX) # the model doesn't need to predict padding index\n    optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate, weight_decay=weight_decay)\n    \n    iters, train_losses, test_losses, mean_test_ranks = [], [], [], []\n    \n    # training\n    n = 0 # the number of iterations\n    for epoch in range(num_epochs):\n        model.train()\n        y_logits = model(X_train_continuous_tensor, X_train_categorical_tensor.long().to(device))\n        loss_train = loss_fn(y_logits, target_train)\n\n        # Backpropagation\n        optimizer.zero_grad() # a clean up step for PyTorch\n        loss_train.backward() # compute updates for each parameter\n        optimizer.step() # make the updates for each parameter\n\n        # save the current training information\n        if n%100 == 0:\n            pred_train = torch.softmax(y_logits, dim=1).argmax(dim=1)\n            acc = accuracy_fn(y_true=target_train, y_pred=pred_train)\n            \n            model.eval()\n            with torch.inference_mode():\n                test_logits = model(X_test_continuous_tensor, X_test_categorical_tensor.long().to(device))\n                test_pred = torch.softmax(test_logits, dim=1).argmax(dim=1)\n                loss_test = loss_fn(test_logits, target_test)\n                test_acc = accuracy_fn(y_true=target_test,y_pred=test_pred)\n            \n            # calculate mean rank on test set\n            softmax = nn.Softmax(dim=0)\n            preds_wnd = softmax(test_logits.float()).cpu().detach().numpy()\n            ranks_wnd = pd.DataFrame(preds_wnd).apply(lambda x: pd.Series(rankdata(-x)), axis=1)\n            ranks_target_wnd = (ranks_wnd.values * target_test_sparse).sum(axis=1)\n            mean_rank_wnd = ranks_target_wnd.mean()\n            \n            print(f\"Epoch: {epoch} | Loss: {loss_train:.5f}, Acc: {acc:.2f}% | Test Loss: {loss_test:.5f}, Test Acc: {test_acc:.2f}% Test mean rank: {mean_rank_wnd:.0f}\")\n            \n            iters.append(n)\n            train_losses.append(float(loss_train))\n            test_losses.append(float(loss_test))\n            mean_test_ranks.append(mean_rank_wnd)\n            \n            # increment the iteration number\n        n += 1\n    \n    # plotting\n    plt.figure(figsize=(12, 8), dpi=100)\n    plt.title(f\"Training Curve (lr={learning_rate})\")\n    plt.plot(iters, train_losses, label=\"Train Loss\")\n    plt.plot(iters, test_losses, label=\"Test Loss\")\n    plt.xlabel(\"Iterations\")\n    plt.ylabel(\"Loss\")\n    plt.legend(loc='best')\n    plt.show()\n    \n    plt.figure(figsize=(12, 8), dpi=100)\n    plt.plot(iters, mean_test_ranks, label=\"Test Rank\")\n    plt.xlabel(\"Iterations\")\n    plt.ylabel(\"Mean Rank on testset\")\n    plt.legend(loc='best')\n    plt.show()\n    \n    return model, iters, train_losses, test_losses","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:26.859532Z","iopub.execute_input":"2022-10-31T06:43:26.860645Z","iopub.status.idle":"2022-10-31T06:43:26.921784Z","shell.execute_reply.started":"2022-10-31T06:43:26.860608Z","shell.execute_reply":"2022-10-31T06:43:26.920153Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"X_train_continuous_tensor, X_test_continuous_tensor, X_train_categorical_tensor, X_test_categorical_tensor, target_train, target_test, target_test_sparse, field_dims, n_classes = load_and_process_data_ffm()","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:26.923234Z","iopub.execute_input":"2022-10-31T06:43:26.924085Z","iopub.status.idle":"2022-10-31T06:43:37.877386Z","shell.execute_reply.started":"2022-10-31T06:43:26.924040Z","shell.execute_reply":"2022-10-31T06:43:37.876393Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"ffm_model = FFM(continuous_dim=X_train_continuous_tensor.shape[1], field_dims=field_dims, n_class=n_classes)","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:37.878649Z","iopub.execute_input":"2022-10-31T06:43:37.879639Z","iopub.status.idle":"2022-10-31T06:43:37.894713Z","shell.execute_reply.started":"2022-10-31T06:43:37.879600Z","shell.execute_reply":"2022-10-31T06:43:37.893780Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"ffm_model_trained, iters, train_losses, test_losses = run_gradient_descent_ffm(ffm_model, num_epochs=1000, weight_decay=0, learning_rate=0.03)","metadata":{"execution":{"iopub.status.busy":"2022-10-31T06:43:37.896216Z","iopub.execute_input":"2022-10-31T06:43:37.896860Z","iopub.status.idle":"2022-10-31T06:46:05.361778Z","shell.execute_reply.started":"2022-10-31T06:43:37.896825Z","shell.execute_reply":"2022-10-31T06:46:05.360863Z"},"trusted":true},"execution_count":7,"outputs":[{"name":"stdout","text":"Epoch: 0 | Loss: 11.90849, Acc: 0.04% | Test Loss: 10.56461, Test Acc: 0.20% Test mean rank: 871\nEpoch: 100 | Loss: 6.09373, Acc: 1.36% | Test Loss: 6.99710, Test Acc: 0.76% Test mean rank: 494\nEpoch: 200 | Loss: 5.96240, Acc: 1.73% | Test Loss: 7.07962, Test Acc: 0.67% Test mean rank: 680\nEpoch: 300 | Loss: 5.90011, Acc: 1.94% | Test Loss: 7.16347, Test Acc: 0.60% Test mean rank: 803\nEpoch: 400 | Loss: 5.86051, Acc: 2.08% | Test Loss: 7.24217, Test Acc: 0.59% Test mean rank: 802\nEpoch: 500 | Loss: 5.83249, Acc: 2.13% | Test Loss: 7.31701, Test Acc: 0.62% Test mean rank: 801\nEpoch: 600 | Loss: 5.81145, Acc: 2.19% | Test Loss: 7.38897, Test Acc: 0.57% Test mean rank: 800\nEpoch: 700 | Loss: 5.79512, Acc: 2.27% | Test Loss: 7.45846, Test Acc: 0.61% Test mean rank: 800\nEpoch: 800 | Loss: 5.78216, Acc: 2.32% | Test Loss: 7.52555, Test Acc: 0.55% Test mean rank: 800\nEpoch: 900 | Loss: 5.77166, Acc: 2.38% | Test Loss: 7.59043, Test Acc: 0.56% Test mean rank: 799\n","output_type":"stream"},{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x800 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}},{"output_type":"display_data","data":{"text/plain":"<Figure size 1200x800 with 1 Axes>","image/png":"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\n"},"metadata":{"needs_background":"light"}}]}]}