SYMBOL INDEX (64 symbols across 16 files)

FILE: analyses/churn_measurements.py
  function calibration (line 17) | def calibration(prob,outcome,n_bins=10):
  function discrimination (line 55) | def discrimination(prob,outcome,n_bins=10):

FILE: deep-learning/keras-tutorial/data_helpers.py
  function clean_str (line 9) | def clean_str(string):
  function load_data_and_labels (line 30) | def load_data_and_labels():
  function pad_sentences (line 51) | def pad_sentences(sentences, padding_word="<PAD/>"):
  function build_vocab (line 66) | def build_vocab(sentences):
  function build_input_data (line 80) | def build_input_data(sentences, labels, vocabulary):
  function load_data (line 89) | def load_data():
  function batch_iter (line 102) | def batch_iter(data, batch_size, num_epochs):

FILE: deep-learning/keras-tutorial/deep_learning_models/imagenet_utils.py
  function preprocess_input (line 11) | def preprocess_input(x, dim_ordering='default'):
  function decode_predictions (line 31) | def decode_predictions(preds):

FILE: deep-learning/keras-tutorial/deep_learning_models/resnet50.py
  function identity_block (line 32) | def identity_block(input_tensor, kernel_size, filters, stage, block):
  function conv_block (line 67) | def conv_block(input_tensor, kernel_size, filters, stage, block, strides...
  function ResNet50 (line 110) | def ResNet50(include_top=True, weights='imagenet',

FILE: deep-learning/keras-tutorial/deep_learning_models/vgg16.py
  function VGG16 (line 30) | def VGG16(include_top=True, weights='imagenet',

FILE: deep-learning/keras-tutorial/deep_learning_models/vgg19.py
  function VGG19 (line 29) | def VGG19(include_top=True, weights='imagenet',

FILE: deep-learning/keras-tutorial/w2v.py
  function train_word2vec (line 6) | def train_word2vec(sentence_matrix, vocabulary_inv,

FILE: deep-learning/tensor-flow-examples/input_data.py
  function maybe_download (line 8) | def maybe_download(filename, work_directory):
  function _read32 (line 18) | def _read32(bytestream):
  function extract_images (line 21) | def extract_images(filename):
  function dense_to_one_hot (line 37) | def dense_to_one_hot(labels_dense, num_classes=10):
  function extract_labels (line 44) | def extract_labels(filename, one_hot=False):
  class DataSet (line 59) | class DataSet(object):
    method __init__ (line 60) | def __init__(self, images, labels, fake_data=False):
    method images (line 81) | def images(self):
    method labels (line 84) | def labels(self):
    method num_examples (line 87) | def num_examples(self):
    method epochs_completed (line 90) | def epochs_completed(self):
    method next_batch (line 92) | def next_batch(self, batch_size, fake_data=False):
  function read_data_sets (line 115) | def read_data_sets(train_dir, fake_data=False, one_hot=False):

FILE: deep-learning/tensor-flow-examples/multigpu_basics.py
  function matpow (line 33) | def matpow(M, n):

FILE: deep-learning/theano-tutorial/intro_theano/utils.py
  function scale_to_unit_interval (line 14) | def scale_to_unit_interval(ndar, eps=1e-8):
  function tile_raster_images (line 22) | def tile_raster_images(X, img_shape, tile_shape, tile_spacing=(0, 0),

FILE: deep-learning/theano-tutorial/rnn_tutorial/rnn_precompile.py
  class SimpleRNN (line 27) | class SimpleRNN(object):
    method __init__ (line 28) | def __init__(self, input_dim, recurrent_dim):
    method _step (line 36) | def _step(self, input_t, previous):
    method __call__ (line 39) | def __call__(self, x):
  function gauss_weight (line 83) | def gauss_weight(rng, ndim_in, ndim_out=None, sd=.005):
  function index_dot (line 90) | def index_dot(indices, w):
  class LstmLayer (line 94) | class LstmLayer:
    method __init__ (line 96) | def __init__(self, rng, input, mask, n_in, n_h):
    method _step (line 132) | def _step(self, m_, x_, h_, c_):
  function sequence_categorical_crossentropy (line 159) | def sequence_categorical_crossentropy(prediction, targets, mask):
  class LogisticRegression (line 169) | class LogisticRegression(object):
    method __init__ (line 171) | def __init__(self, rng, input, n_in, n_out):

FILE: deep-learning/theano-tutorial/rnn_tutorial/synthetic.py
  function mackey_glass (line 5) | def mackey_glass(sample_len=1000, tau=17, seed=None, n_samples = 1):
  function mso (line 46) | def mso(sample_len=1000, n_samples = 1):
  function lorentz (line 62) | def lorentz(sample_len=1000, sigma=10, rho=28, beta=8 / 3, step=0.01):

FILE: deep-learning/theano-tutorial/scan_tutorial/scan_ex1_solution.py
  function step (line 10) | def step(coeff, power, prior_value, free_var):

FILE: deep-learning/theano-tutorial/scan_tutorial/scan_ex2_solution.py
  function sample_from_pvect (line 11) | def sample_from_pvect(pvect):
  function set_p_to_zero (line 21) | def set_p_to_zero(pvect, i):
  function step (line 32) | def step(p):

FILE: mapreduce/mr_s3_log_parser.py
  class MrS3LogParser (line 8) | class MrS3LogParser(MRJob):
    method clean_date_time_zone (line 56) | def clean_date_time_zone(self, raw_date_time_zone):
    method mapper (line 88) | def mapper(self, _, line):
    method reducer (line 121) | def reducer(self, key, values):
    method steps (line 129) | def steps(self):

FILE: mapreduce/test_mr_s3_log_parser.py
  class MrTestsUtil (line 7) | class MrTestsUtil:
    method run_mr_sandbox (line 9) | def run_mr_sandbox(self, mr_job, stdin):
  class TestMrS3LogParser (line 26) | class TestMrS3LogParser(unittest.TestCase):
    method __init__ (line 56) | def __init__(self, *args, **kwargs):
    method test_invalid_log_lines (line 61) | def test_invalid_log_lines(self):
    method test_valid_log_lines (line 67) | def test_valid_log_lines(self):
    method test_clean_date_time_zone (line 73) | def test_clean_date_time_zone(self):