Data transformation (TF Transform) in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Data transformation (TF Transform)

Which metric matters for Data transformation (TF Transform) and WHY

When we transform data using TF Transform, the main goal is to prepare data so the model learns well. We check if the transformed data keeps the original meaning and helps the model perform better. Metrics like mean, variance, and distribution similarity before and after transformation matter. These show if the data is changed correctly without losing important info.

Confusion matrix or equivalent visualization

For data transformation, we don't use a confusion matrix. Instead, we compare statistics of data before and after transformation. For example:

Original feature 'age':
  Mean = 35.0
  Std Dev = 10.0

Transformed feature 'age_scaled':
  Mean = 0.0
  Std Dev = 1.0

This shows the data was scaled correctly.
    

Tradeoff: Data transformation quality vs model performance

Good data transformation makes the model learn faster and better. But if transformation is too complex or wrong, it can confuse the model. For example, scaling features helps models that expect numbers in a certain range. But if you scale test data differently than training data, the model will perform badly. So, the tradeoff is between simple, consistent transformations and complex ones that might cause errors.

What "good" vs "bad" data transformation looks like

Good: Transformed data has similar distribution shape, expected mean and variance, and no missing or invalid values. The model trained on transformed data shows improved accuracy or loss.

Bad: Transformed data has unexpected values (like negatives where only positives make sense), very different distribution, or inconsistent scaling. Model performance drops or becomes unstable.

Common pitfalls in data transformation metrics

• Not applying the same transformation to training and test data causes poor model results.
• Data leakage: Using information from test data during transformation can give overly optimistic results.
• Ignoring missing or invalid values during transformation leads to errors or bad model behavior.
• Assuming transformed data is good without checking statistics or model metrics.

Self-check question

Your model trained on transformed data has 98% accuracy but the transformed test data has a mean very different from training data. Is this good?

Answer: No. The difference in mean suggests the test data was transformed differently. This can cause the model to perform poorly on new data even if accuracy looks high now. You should fix the transformation to be consistent.

Key Result

Check data statistics before and after transformation to ensure consistent, meaningful changes that improve model learning.

Practice

1. What is the main purpose of TF Transform in machine learning pipelines?

easy

A. To visualize the dataset statistics

B. To train the machine learning model faster

C. To apply consistent data transformations during both training and serving

D. To generate synthetic data samples

Solution

1. Step 1: Understand TF Transform's role

   TF Transform is designed to apply the same data transformations consistently during training and serving.

2. Step 2: Compare options

   Options A, B, and D describe other tasks unrelated to TF Transform's main purpose.

3. Final Answer:

   To apply consistent data transformations during both training and serving -> Option C

4. Quick Check:

   Consistent transformations = To apply consistent data transformations during both training and serving [OK]

Hint: TF Transform ensures same data changes in training and serving [OK]

Common Mistakes:

• Confusing TF Transform with model training
• Thinking TF Transform generates data
• Assuming it visualizes data statistics

2. Which of the following is the correct way to define a TF Transform preprocessing function that scales a numeric feature named age by its mean and variance?

easy

A. def preprocessing_fn(inputs):
age = tft.scale_to_z_score(inputs['age'])
return {'age_scaled': age}

B. def preprocessing_fn(inputs):
return {'age_scaled': inputs['age'] / 100}

C. def preprocessing_fn(inputs):
return {'age_scaled': inputs['age'] + 10}

D. def preprocessing_fn(inputs):
age = inputs['age'] * 2
return {'age_scaled': age}

Solution

1. Step 1: Identify correct TF Transform scaling function

   TF Transform provides tft.scale_to_z_score to scale features by mean and variance.

2. Step 2: Check code correctness

   def preprocessing_fn(inputs): age = tft.scale_to_z_score(inputs['age']) return {'age_scaled': age} uses tft.scale_to_z_score correctly; others use incorrect or arbitrary scaling.

3. Final Answer:

   def preprocessing_fn(inputs): age = tft.scale_to_z_score(inputs['age']) return {'age_scaled': age} -> Option A

4. Quick Check:

   Use tft.scale_to_z_score for mean-variance scaling [OK]

Hint: Use tft.scale_to_z_score for standard scaling [OK]

Common Mistakes:

• Using simple division instead of TF Transform scaling
• Adding arbitrary constants instead of scaling
• Multiplying without normalization

3. Given the following TF Transform preprocessing function, what will be the output for input {'income': 50000} if the dataset mean income is 40000 and stddev is 10000?

def preprocessing_fn(inputs):
    income_scaled = tft.scale_to_z_score(inputs['income'])
    return {'income_scaled': income_scaled}

medium

A. {'income_scaled': 0.0}

B. {'income_scaled': 0.5}

C. {'income_scaled': -1.0}

D. {'income_scaled': 1.0}

Solution

1. Step 1: Calculate z-score for income

   Z-score = (value - mean) / stddev = (50000 - 40000) / 10000 = 1.0

2. Step 2: Match output format

   The function returns {'income_scaled': z-score}, so output is {'income_scaled': 1.0}

3. Final Answer:

   {'income_scaled': 1.0} -> Option D

4. Quick Check:

   Z-score calculation = 1.0 [OK]

Hint: Z-score = (value - mean) / stddev for scaling [OK]

Common Mistakes:

• Forgetting to subtract mean
• Dividing by mean instead of stddev
• Mixing up positive and negative signs

4. You wrote this TF Transform preprocessing function but get an error during analysis:

def preprocessing_fn(inputs):
    age_bucketized = tft.bucketize(inputs['age'], num_buckets=5)
    return {'age_bucketized': age_bucketized}

What is the likely cause of the error?

medium

A. The input 'age' is not a numeric tensor

B. The function tft.bucketize requires 'boundaries' instead of 'num_buckets'

C. Missing import statement for tensorflow_transform as tft

D. The return value must be a list, not a dictionary

Solution

1. Step 1: Check tft.bucketize function signature

   tft.bucketize requires 'boundaries' argument, not 'num_buckets'.

2. Step 2: Identify error cause

   Using 'num_buckets' causes an error because it's not a valid parameter.

3. Final Answer:

   The function tft.bucketize requires 'boundaries' instead of 'num_buckets' -> Option B

4. Quick Check:

   tft.bucketize needs boundaries, not num_buckets [OK]

Hint: Use boundaries list for tft.bucketize, not num_buckets [OK]

Common Mistakes:

• Passing num_buckets instead of boundaries
• Forgetting to import tensorflow_transform
• Returning wrong data type

5. You want to apply TF Transform to prepare a dataset with numeric feature height and categorical feature color. You want to scale height and one-hot encode color. Which preprocessing function correctly applies these transformations?

hard

A. def preprocessing_fn(inputs):
height_scaled = tft.scale_to_z_score(inputs['height'])
color_vocab = tft.compute_and_apply_vocabulary(inputs['color'])
color_one_hot = tf.one_hot(color_vocab, depth=3)
return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot}

B. def preprocessing_fn(inputs):
height_scaled = tft.scale_to_z_score(inputs['height'])
color_one_hot = tft.compute_and_apply_vocabulary(inputs['color'])
return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot}

C. def preprocessing_fn(inputs):
height_scaled = inputs['height'] / 100
color_one_hot = tf.one_hot(inputs['color'], depth=3)
return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot}

D. def preprocessing_fn(inputs):
height_scaled = tft.scale_to_z_score(inputs['height'])
color_one_hot = tf.one_hot(inputs['color'], depth=3)
return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot}

Solution

1. Step 1: Scale numeric feature 'height'

   Use tft.scale_to_z_score to scale 'height' correctly.

2. Step 2: One-hot encode categorical 'color'

   First, map 'color' to integer indices using tft.compute_and_apply_vocabulary, then apply tf.one_hot with correct depth.

3. Step 3: Verify options

   def preprocessing_fn(inputs): height_scaled = tft.scale_to_z_score(inputs['height']) color_vocab = tft.compute_and_apply_vocabulary(inputs['color']) color_one_hot = tf.one_hot(color_vocab, depth=3) return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot} correctly chains vocabulary computation and one-hot encoding; others miss steps or misuse functions.

4. Final Answer:

   def preprocessing_fn(inputs): height_scaled = tft.scale_to_z_score(inputs['height']) color_vocab = tft.compute_and_apply_vocabulary(inputs['color']) color_one_hot = tf.one_hot(color_vocab, depth=3) return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot} -> Option A

5. Quick Check:

   Vocabulary then one-hot encoding = def preprocessing_fn(inputs): height_scaled = tft.scale_to_z_score(inputs['height']) color_vocab = tft.compute_and_apply_vocabulary(inputs['color']) color_one_hot = tf.one_hot(color_vocab, depth=3) return {'height_scaled': height_scaled, 'color_one_hot': color_one_hot} [OK]

Hint: Use vocabulary lookup before one-hot encoding categorical data [OK]

Common Mistakes:

• Applying one-hot directly on strings
• Skipping vocabulary computation
• Scaling numeric features incorrectly