Data transformation (TF Transform) in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create a TF Transform preprocessing function that scales a numeric feature.

TensorFlow

def preprocessing_fn(inputs):
    import tensorflow_transform as tft
    x = inputs['feature']
    x_scaled = tft.[1](x)
    return {'feature_scaled': x_scaled}

Drag options to blanks, or click blank then click option'

Ascale_to_z_score

Bbucketize

Cnormalize

Dscale_to_0_1

Attempts:

3 left

💡 Hint

Common Mistakes

Using bucketize instead of scaling for numeric features.

Using scale_to_0_1 which scales between 0 and 1, not zero mean and unit variance.

The function tft.scale_to_z_score scales numeric features to have zero mean and unit variance, which is a common normalization step.

2fill in blank

medium

Complete the code to apply TF Transform's vocabulary function to a categorical feature.

TensorFlow

def preprocessing_fn(inputs):
    import tensorflow_transform as tft
    x = inputs['category']
    x_vocab = tft.[1](x)
    return {'category_vocab': x_vocab}

Drag options to blanks, or click blank then click option'

Abucketize

Bcompute_and_apply_vocabulary

Cscale_to_0_1

Dscale_to_z_score

Attempts:

3 left

💡 Hint

Common Mistakes

Using scaling functions on categorical data.

Using bucketize which is for numeric data binning.

The function tft.compute_and_apply_vocabulary creates a vocabulary from the categorical feature and maps the input to integer indices.

3fill in blank

hard

Fix the error in the TF Transform preprocessing function that tries to bucketize a numeric feature.

TensorFlow

def preprocessing_fn(inputs):
    import tensorflow_transform as tft
    x = inputs['age']
    x_buckets = tft.[1](x, num_buckets=5)
    return {'age_buckets': x_buckets}

Drag options to blanks, or click blank then click option'

Ascale_to_z_score

Bcompute_and_apply_vocabulary

Cbucketize

Dscale_to_0_1

Attempts:

3 left

💡 Hint

Common Mistakes

Using scaling functions instead of bucketizing.

Using vocabulary functions on numeric data.

The function tft.bucketize splits numeric data into buckets. The code needs 'bucketize' to create age buckets.

4fill in blank

hard

Fill both blanks to create a TF Transform preprocessing function that normalizes a numeric feature and buckets another feature.

TensorFlow

def preprocessing_fn(inputs):
    import tensorflow_transform as tft
    x_num = inputs['income']
    x_cat = inputs['education']
    income_norm = tft.[1](x_num)
    education_buckets = tft.[2](x_cat, num_buckets=4)
    return {'income_norm': income_norm, 'education_buckets': education_buckets}

Drag options to blanks, or click blank then click option'

Ascale_to_z_score

Bcompute_and_apply_vocabulary

Cbucketize

Dscale_to_0_1

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing vocabulary functions with numeric bucketing.

Using scale_to_0_1 instead of scale_to_z_score for normalization.

Income is normalized with scale_to_z_score, and education is bucketized into 4 buckets.

5fill in blank

hard

Fill all three blanks to create a TF Transform preprocessing function that applies vocabulary to a categorical feature, normalizes a numeric feature, and buckets another numeric feature.

TensorFlow

def preprocessing_fn(inputs):
    import tensorflow_transform as tft
    cat_feat = inputs['city']
    num_feat1 = inputs['temperature']
    num_feat2 = inputs['humidity']
    city_vocab = tft.[1](cat_feat)
    temp_norm = tft.[2](num_feat1)
    humidity_buckets = tft.[3](num_feat2, num_buckets=3)
    return {'city_vocab': city_vocab, 'temp_norm': temp_norm, 'humidity_buckets': humidity_buckets}

Drag options to blanks, or click blank then click option'

Acompute_and_apply_vocabulary

Bscale_to_z_score

Cbucketize

Dscale_to_0_1

Attempts:

3 left

💡 Hint

Common Mistakes

Using bucketize on categorical features.

Using scale_to_0_1 instead of scale_to_z_score for normalization.

Vocabulary is applied to city, temperature is normalized with scale_to_z_score, and humidity is bucketized into 3 buckets.

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