Use pathlib to get abs-file-path of csv files from the the project directory

[cuicaihao]

Replace the following code from

import tensorflow as tf
# Training samples path, change to your local path
training_samples_file_path = tf.keras.utils.get_file("trainingSamples.csv",
                                                     "file:///Users/zhewang/Workspace/SparrowRecSys/src/main"
                                                     "/resources/webroot/sampledata/trainingSamples.csv")
# Test samples path, change to your local path
test_samples_file_path = tf.keras.utils.get_file("testSamples.csv",
                                                 "file:///Users/zhewang/Workspace/SparrowRecSys/src/main"
                                                 "/resources/webroot/sampledata/testSamples.csv")

to

import tensorflow as tf
import pathlib
current_working_directory = pathlib.Path().absolute()
train_abs_path = current_working_directory / \
    "src/main/resources/webroot/sampledata/trainingSamples.csv"
test_abs_path = current_working_directory / \
    "src/main/resources/webroot/sampledata/testSamples.csv"

#  check the file paths 
print(train_abs_path)
print(test_abs_path)

# Training samples path, change to your local path
training_samples_file_path = tf.keras.utils.get_file("trainingSamples.csv",
                                                     "file://" + str(train_abs_path))
# Test samples path, change to your local path
test_samples_file_path = tf.keras.utils.get_file("testSamples.csv",
                                                 "file://" + str(test_abs_path))

Test command can be:

# cd PATH-TO-PROJECT
(base) ➜  SparrowRecSys git:(master) ✗ python TFRecModel/src/com/sparrowrecsys/offline/tensorflow/EmbeddingMLP.py 

Terminal output will be like:

(base) ➜  SparrowRecSys git:(master) ✗ python TFRecModel/src/com/sparrowrecsys/offline/tensorflow/EmbeddingMLP.py 
  
/Users/caihaocui/Documents/GitHub/SparrowRecSys/src/main/resources/webroot/sampledata/trainingSamples.csv
/Users/caihaocui/Documents/GitHub/SparrowRecSys/src/main/resources/webroot/sampledata/testSamples.csv

2021-05-01 23:34:19.899459: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set
2021-05-01 23:34:19.899750: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2021-05-01 23:34:20.127706: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:116] None of the MLIR optimization passes are enabled (registered 2)
Epoch 1/5
7403/7403 [==============================] - 23s 3ms/step - loss: 6.2921 - accuracy: 0.5508 - auc: 0.5540 - auc_1: 0.6035
Epoch 2/5
7403/7403 [==============================] - 25s 3ms/step - loss: 0.6940 - accuracy: 0.6447 - auc: 0.6820 - auc_1: 0.7157
Epoch 3/5
7403/7403 [==============================] - 26s 3ms/step - loss: 0.5712 - accuracy: 0.7060 - auc: 0.7657 - auc_1: 0.7862
Epoch 4/5
7403/7403 [==============================] - 25s 3ms/step - loss: 0.5235 - accuracy: 0.7434 - auc: 0.8117 - auc_1: 0.8311
Epoch 5/5
7403/7403 [==============================] - 28s 4ms/step - loss: 0.5019 - accuracy: 0.7550 - auc: 0.8295 - auc_1: 0.8507
1870/1870 [==============================] - 3s 1ms/step - loss: 0.5930 - accuracy: 0.6951 - auc: 0.7545 - auc_1: 0.7811
Test Loss 0.5929673314094543, Test Accuracy 0.6950534582138062, Test ROC AUC 0.7545442581176758, Test PR AUC 0.7810750603675842
WARNING:tensorflow:Layers in a Sequential model should only have a single input tensor, but we receive ... ... 
Predicted good rating: 92.50%  | Actual rating label:  Good Rating
Predicted good rating: 15.49%  | Actual rating label:  Bad Rating
Predicted good rating: 51.89%  | Actual rating label:  Good Rating
Predicted good rating: 74.08%  | Actual rating label:  Good Rating
Predicted good rating: 66.84%  | Actual rating label:  Good Rating
Predicted good rating: 92.49%  | Actual rating label:  Good Rating
Predicted good rating: 13.64%  | Actual rating label:  Good Rating
Predicted good rating: 35.65%  | Actual rating label:  Good Rating
Predicted good rating: 11.24%  | Actual rating label:  Bad Rating
Predicted good rating: 88.39%  | Actual rating label:  Good Rating
Predicted good rating: 42.15%  | Actual rating label:  Bad Rating
Predicted good rating: 90.55%  | Actual rating label:  Bad Rating
(base) ➜  SparrowRecSys git:(master) ✗