TEST: Fix distributed examples not being executed (#2693)

* put daal4py distributed examples under 'main()' body

* fix incorrect data paths

Author: david-cortes-intel

examples/daal4py/linear_regression_spmd.py

@@ -18,18 +18,17 @@
 # run like this:
 #    mpirun -n 4 python ./linreg_spmd.py
 
+from pathlib import Path
+
 from numpy import loadtxt
 
 import daal4py as d4p
 
-if __name__ == "__main__":
-    # Initialize SPMD mode
-    d4p.daalinit()
 
+def main():
     # Each process gets its own data
-    infile = (
-        "./data/distributed/linear_regression_train_" + str(d4p.my_procid() + 1) + ".csv"
-    )
+    data_path = Path(__file__).parent / "data" / "distributed"
+    infile = data_path / f"linear_regression_train_{d4p.my_procid() + 1}.csv"
 
     # Configure a Linear regression training object
     train_algo = d4p.linear_regression_training(distributed=True)
@@ -47,7 +46,7 @@
         predict_algo = d4p.linear_regression_prediction()
         # read test data (with same #features)
         pdata = loadtxt(
-            "./data/distributed/linear_regression_test.csv",
+            data_path / "linear_regression_test.csv",
             delimiter=",",
             usecols=range(10),
         )
@@ -59,5 +58,10 @@
         # The prediction result provides prediction
         assert predict_result.prediction.shape == (pdata.shape[0], dep_data.shape[1])
 
+
+if __name__ == "__main__":
+    # Initialize SPMD mode
+    d4p.daalinit()
+    main()
     print("All looks good!")
     d4p.daalfini()

examples/daal4py/naive_bayes_spmd.py

@@ -24,12 +24,10 @@
 
 import daal4py as d4p
 
-if __name__ == "__main__":
-    # Initialize SPMD mode
-    d4p.daalinit()
 
+def main():
     # Each process gets its own data
-    data_path = Path(__file__).parent / "data" / "batch"
+    data_path = Path(__file__).parent / "data" / "distributed"
     infile = data_path / "naivebayes_train_dense.csv"
 
     # Configure a training object (20 classes)
@@ -47,14 +45,18 @@
         palgo = d4p.multinomial_naive_bayes_prediction(20)
         # read test data (with same #features)
         pdata = loadtxt(
-            "./data/batch/naivebayes_test_dense.csv", delimiter=",", usecols=range(20)
+            data_path / "naivebayes_test_dense.csv", delimiter=",", usecols=range(20)
         )
         # now predict using the model from the training above
         presult = palgo.compute(pdata, tresult.model)
 
         # Prediction result provides prediction
         assert presult.prediction.shape == (pdata.shape[0], 1)
 
-        print("All looks good!")
 
+if __name__ == "__main__":
+    # Initialize SPMD mode
+    d4p.daalinit()
+    main()
+    print("All looks good!")
     d4p.daalfini()

examples/daal4py/pca_spmd.py

@@ -24,10 +24,8 @@
 
 import daal4py as d4p
 
-if __name__ == "__main__":
-    # Initialize SPMD mode
-    d4p.daalinit()
 
+def main():
     # Each process gets its own data
     data_path = Path(__file__).parent / "data" / "distributed"
     infile = data_path / f"pca_normalized_{d4p.my_procid() + 1}.csv"
@@ -55,5 +53,10 @@
         or allclose(result1.variances, result2.variances)
     )
 
+
+if __name__ == "__main__":
+    # Initialize SPMD mode
+    d4p.daalinit()
+    main()
     print("All looks good!")
     d4p.daalfini()

examples/daal4py/ridge_regression_spmd.py

@@ -18,19 +18,17 @@
 # run like this:
 #    mpirun -n 4 python ./ridge_regression_spmd.py
 
+from pathlib import Path
 
 from numpy import loadtxt
 
 import daal4py as d4p
 
-if __name__ == "__main__":
-    # Initialize SPMD mode
-    d4p.daalinit()
 
+def main():
     # Each process gets its own data
-    infile = (
-        "./data/distributed/linear_regression_train_" + str(d4p.my_procid() + 1) + ".csv"
-    )
+    data_path = Path(__file__).parent / "data" / "distributed"
+    infile = data_path / f"linear_regression_train_{d4p.my_procid() + 1}.csv"
 
     # Configure a Ridge regression training object
     train_algo = d4p.ridge_regression_training(distributed=True)
@@ -48,7 +46,7 @@
         predict_algo = d4p.ridge_regression_prediction()
         # read test data (with same #features)
         pdata = loadtxt(
-            "./data/distributed/linear_regression_test.csv",
+            data_path / "linear_regression_test.csv",
             delimiter=",",
             usecols=range(10),
         )
@@ -60,5 +58,10 @@
         # The prediction result provides prediction
         assert predict_result.prediction.shape == (pdata.shape[0], dep_data.shape[1])
 
+
+if __name__ == "__main__":
+    # Initialize SPMD mode
+    d4p.daalinit()
+    main()
     print("All looks good!")
     d4p.daalfini()

tests/test_daal4py_spmd_examples.py

@@ -183,6 +183,8 @@ def test_dbscan_spmd(self):
     if "spmd" not in fname:
         # here we only run spmd examples
         continue
+    if "spmd_chunks_read" in fname:
+        continue
     stem = Path(fname).stem
     if stem in module_names_with_configs:
         continue