crawles

explanation_metadata = {
    "inputs": {
      "dayofweek": {
        "input_tensor_name": "dayofweek:0",
        "input_baselines": [baselines_mode[0][0]] # Thursday
      },
      "hourofday": {
        "input_tensor_name": "hourofday:0",
        "input_baselines": [baselines_mode[0][1]] # 8pm
      },

crawles

from io import StringIO

def head(table, n=10):
    head_list = !bq head --n $n --table $table
    head_str = '\n'.join([head_list[1]] + head_list[3:-1])
    return pd.read_csv(StringIO(head_str), delimiter="|").iloc[:, 1:-1]
    
df = head('publicdata:samples.natality')

crawles

def permutation_importances(est, X_eval, y_eval, metric, features):
    """Column by column, shuffle values and observe effect on eval set.
        source: http://explained.ai/rf-importance/index.html
    A similar approach can be done during training. See "Drop-column importance"
    in the above article."""
    def accuracy_metric(est, X, y):
        """TensorFlow estimator accuracy."""
        eval_input_fn = make_input_fn(X,
                                      y=y,
                                      shuffle=False,

crawles

# Get importances
importances = est.experimental_feature_importances(normalize=True)
df_imp = pd.Series(importances)

# Visualize importances.
N = 8
ax = (df_imp.iloc[0:N][::-1]
    .plot(kind='barh'))

crawles

# Make predictions.
pred_dicts = list(est.experimental_predict_with_explanations(eval_input_fn))
df_dfc = pd.DataFrame([pred['dfc'] for pred in pred_dicts])
# Plot results.
ID = 182
example = df_dfc.iloc[ID]  # Choose ith example from evaluation set.
TOP_N = 8  # View top 8 features.
sorted_ix = example.abs().sort_values()[-TOP_N:].index
ax = example[sorted_ix].plot(kind='barh')

crawles

params = {
  'n_trees': 50,
  'max_depth': 3,
  'n_batches_per_layer': 1,
  # You must enable center_bias = True to get DFCs. This will force the model to 
  # make an initial prediction before using any features (e.g. use the mean of 
  # the training labels for regression or log odds for classification when
  # using cross entropy loss).
  'center_bias': True
}

crawles

# Since data fits into memory, use entire dataset per layer. It will be faster.
# Above one batch is defined as the entire dataset. 
n_batches = 1
est = tf.estimator.BoostedTreesClassifier(feature_columns,
                                          n_batches_per_layer=n_batches)

# The model will stop training once the specified number of trees is built, not 
# based on the number of steps.
est.train(train_input_fn, max_steps=100)

crawles

linear_est = tf.estimator.LinearClassifier(feature_columns)

# Train model.
linear_est.train(train_input_fn, max_steps=100)

# Evaluation.
result = linear_est.evaluate(eval_input_fn)

crawles

# Use entire batch since this is such a small dataset.
NUM_EXAMPLES = len(y_train)

def make_input_fn(X, y, n_epochs=None, shuffle=True):
  def input_fn():
    dataset = tf.data.Dataset.from_tensor_slices((dict(X), y))
    if shuffle:
      dataset = dataset.shuffle(NUM_EXAMPLES)
    # For training, cycle thru dataset as many times as need (n_epochs=None).    
    dataset = dataset.repeat(n_epochs)

crawles

example = dict(dftrain.head(1))
class_fc = tf.feature_column.indicator_column(tf.feature_column.categorical_column_with_vocabulary_list('class', ('First', 'Second', 'Third')))
print('Feature value: "{}"'.format(example['class'].iloc[0]))
print('One-hot encoded: ', tf.keras.layers.DenseFeatures([class_fc])(example).numpy())

# Feature value: "Third"
# One-hot encoded:  [[0. 0. 1.]]