Data loading portion of train.py

train.py

@@ -0,0 +1,30 @@
+"""
+train.py
+
+Launches the training process for the model.
+"""
+
+from pathlib import Path
+
+from pipe.pipe import SpectrogramPipe
+from pyspark.sql import SparkSession
+
+def main():
+    path = Path("/app/datadump/train")
+
+    labels = []
+    with open(path / "train.csv", "r") as file:
+        for line in file:
+            labels.append(line.strip().split(","))
+
+    spark = SparkSession.builder.appName("train").getOrCreate()
+    pipe = SpectrogramPipe(spark)
+    data = pipe.spectrogram_pipe(path, labels)
+    print(data.head())
+
+    return
+
+if __name__ == "__main__":
+    main()
+
+# EOF