test: run examples smoke tests in CI

Author: shenweichen

.github/workflows/ci.yml

@@ -5,12 +5,14 @@ on:
     paths:
       - "deepctr_torch/**"
       - "tests/**"
+      - "examples/**"
       - "setup.py"
       - ".github/workflows/**"
   pull_request:
     paths:
       - "deepctr_torch/**"
       - "tests/**"
+      - "examples/**"
       - "setup.py"
       - ".github/workflows/**"
   workflow_dispatch:
@@ -37,6 +39,7 @@ jobs:
             torch-version: "2.4.1"
           - python-version: "3.10"
             torch-version: "2.5.1"
+            run-examples: "1"
           - python-version: "3.11"
             torch-version: "2.4.1"
           - python-version: "3.11"
@@ -49,6 +52,7 @@ jobs:
     env:
       TORCH_VERSION: ${{ matrix.torch-version }}
       TORCH_INDEX_URL: https://download.pytorch.org/whl/cpu
+      RUN_EXAMPLES: ${{ matrix.run-examples || '0' }}
 
     steps:
       - uses: actions/checkout@v5
@@ -65,6 +69,11 @@ jobs:
         timeout-minutes: 180
         run: bash tests/ci/test.sh
 
+      - name: Run examples smoke tests
+        if: ${{ env.RUN_EXAMPLES == '1' }}
+        timeout-minutes: 60
+        run: bash tests/ci/examples.sh
+
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v6
         with:

examples/run_classification_criteo.py

@@ -1,4 +1,6 @@
 # -*- coding: utf-8 -*-
+import os
+
 import pandas as pd
 import torch
 from sklearn.metrics import log_loss, roc_auc_score
@@ -58,7 +60,8 @@
     model.compile("adagrad", "binary_crossentropy",
                   metrics=["binary_crossentropy", "auc"], )
 
-    history = model.fit(train_model_input, train[target].values, batch_size=32, epochs=10, verbose=2,
+    epochs = int(os.getenv("DEEPCTR_EXAMPLE_EPOCHS", "10"))
+    history = model.fit(train_model_input, train[target].values, batch_size=32, epochs=epochs, verbose=2,
                         validation_split=0.2)
     pred_ans = model.predict(test_model_input, 256)
     print("")

examples/run_dien.py

@@ -1,3 +1,4 @@
+import os
 import numpy as np
 import torch
 
@@ -65,4 +66,5 @@ def get_xy_fd(use_neg=False, hash_flag=False):
 
     model.compile('adam', 'binary_crossentropy',
                   metrics=['binary_crossentropy', 'auc'])
-    history = model.fit(x, y, batch_size=2, epochs=10, verbose=1, validation_split=0, shuffle=False)
+    epochs = int(os.getenv("DEEPCTR_EXAMPLE_EPOCHS", "10"))
+    history = model.fit(x, y, batch_size=2, epochs=epochs, verbose=1, validation_split=0, shuffle=False)

examples/run_din.py

@@ -2,6 +2,7 @@
 
 sys.path.insert(0, '..')
 
+import os
 import numpy as np
 import torch
 from deepctr_torch.inputs import (DenseFeat, SparseFeat, VarLenSparseFeat,
@@ -47,4 +48,5 @@ def get_xy_fd():
     model = DIN(feature_columns, behavior_feature_list, device=device, att_weight_normalization=True)
     model.compile('adagrad', 'binary_crossentropy',
                   metrics=['binary_crossentropy'])
-    history = model.fit(x, y, batch_size=3, epochs=10, verbose=2, validation_split=0.0)
+    epochs = int(os.getenv("DEEPCTR_EXAMPLE_EPOCHS", "10"))
+    history = model.fit(x, y, batch_size=3, epochs=epochs, verbose=2, validation_split=0.0)

examples/run_multitask_learning.py

@@ -1,4 +1,6 @@
 # -*- coding: utf-8 -*-
+import os
+
 import pandas as pd
 import torch
 from sklearn.metrics import log_loss, roc_auc_score
@@ -56,7 +58,8 @@
     model.compile("adagrad", loss=["binary_crossentropy", "binary_crossentropy"],
                   metrics=['binary_crossentropy'], )
 
-    history = model.fit(train_model_input, train[target].values, batch_size=32, epochs=10, verbose=2)
+    epochs = int(os.getenv("DEEPCTR_EXAMPLE_EPOCHS", "10"))
+    history = model.fit(train_model_input, train[target].values, batch_size=32, epochs=epochs, verbose=2)
     pred_ans = model.predict(test_model_input, 256)
     print("")
     for i, target_name in enumerate(target):

examples/run_multivalue_movielens.py

@@ -1,8 +1,28 @@
+import os
+
 import numpy as np
 import pandas as pd
 import torch
 from sklearn.preprocessing import LabelEncoder
-from tensorflow.python.keras.preprocessing.sequence import pad_sequences
+
+try:
+    from tensorflow.keras.preprocessing.sequence import pad_sequences
+except Exception:
+    def pad_sequences(sequences, maxlen=None, dtype='int32', padding='pre', truncating='pre', value=0):
+        if maxlen is None:
+            maxlen = max(len(seq) for seq in sequences)
+        x = np.full((len(sequences), maxlen), value, dtype=dtype)
+        for idx, seq in enumerate(sequences):
+            if truncating == 'pre':
+                trunc = seq[-maxlen:]
+            else:
+                trunc = seq[:maxlen]
+            trunc = np.asarray(trunc, dtype=dtype)
+            if padding == 'post':
+                x[idx, :len(trunc)] = trunc
+            else:
+                x[idx, -len(trunc):] = trunc
+        return x
 
 from deepctr_torch.inputs import SparseFeat, VarLenSparseFeat, get_feature_names
 from deepctr_torch.models import DeepFM
@@ -64,4 +84,6 @@ def split(x):
     model = DeepFM(linear_feature_columns, dnn_feature_columns, task='regression', device=device)
 
     model.compile("adam", "mse", metrics=['mse'], )
-    history = model.fit(model_input, data[target].values, batch_size=256, epochs=10, verbose=2, validation_split=0.2)
+    epochs = int(os.getenv("DEEPCTR_EXAMPLE_EPOCHS", "10"))
+    history = model.fit(model_input, data[target].values, batch_size=256, epochs=epochs, verbose=2,
+                        validation_split=0.2)

examples/run_regression_movielens.py

@@ -1,3 +1,5 @@
+import os
+
 import pandas as pd
 import torch
 from sklearn.metrics import mean_squared_error
@@ -40,7 +42,8 @@
     model = DeepFM(linear_feature_columns, dnn_feature_columns, task='regression', device=device)
     model.compile("adam", "mse", metrics=['mse'], )
 
-    history = model.fit(train_model_input, train[target].values, batch_size=256, epochs=10, verbose=2,
+    epochs = int(os.getenv("DEEPCTR_EXAMPLE_EPOCHS", "10"))
+    history = model.fit(train_model_input, train[target].values, batch_size=256, epochs=epochs, verbose=2,
                         validation_split=0.2)
     pred_ans = model.predict(test_model_input, batch_size=256)
     print("test MSE", round(mean_squared_error(

tests/ci/examples.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+export DEEPCTR_EXAMPLE_EPOCHS="${DEEPCTR_EXAMPLE_EPOCHS:-1}"
+
+scripts=(
+  "run_classification_criteo.py"
+  "run_regression_movielens.py"
+  "run_multitask_learning.py"
+  "run_multivalue_movielens.py"
+  "run_din.py"
+  "run_dien.py"
+)
+
+pushd examples >/dev/null
+for script in "${scripts[@]}"; do
+  echo "Running example smoke test: ${script} (epochs=${DEEPCTR_EXAMPLE_EPOCHS})"
+  python "${script}"
+done
+popd >/dev/null

tests/ci/install.sh

@@ -10,6 +10,6 @@ else
   python -m pip install -q "torch==${TORCH_VERSION}"
 fi
 
-python -m pip install -q requests pytest pytest-cov python-coveralls
+python -m pip install -q requests pytest pytest-cov python-coveralls pandas
 python -m pip install -e .
 python -m pip check