Loading multiple csvs with mixed dtypes in tensorflow for training - csv

Question

I have 100s of csvs in a directory, with headers. I am trying to create a feedforward NN using tensorflow for regression.
What's the best way to import these csvs and train using tf & train it?
Also help to look at my preprocessing if I am doing it right?
Note: My features has mixed datatypes (int,float,string), My target is float
I can not concat the csv and use pandas to import, my data size is >50 GB so can not load it in-memory, have to read it iteratively from disc
Directory Path:
./data/train/ -> 100s of csvs
./data/test -> 100s of csvs
./data/valid -> 100s of csvs
Code:
Methodology:
Create Generator
Use Dataset API to load the data
Preprocess the Data (embedding, one-hot,etc)
Train fit
But, in generator I was able to give only output formats where the inputs/ outputs are homogeneous ddtypes.
Code:
def data_generator(file_list, batch_size = 2):
i = 0
while True:
if i*batch_size >= len(file_list): # This loop is used to run the generator indefinitely.
i = 0
np.random.shuffle(file_list)
else:
file_chunk = file_list[i*batch_size:(i+1)*batch_size]
data = []
labels = []
for file in file_chunk:
temp = pd.read_csv(open(file,'r')) # Change this line to read any other type of file
labels = temp.pop('ACTUAL_BOXES')
data.append(temp.values) # Convert column data to matrix like data with one channel
labels.append(labels)
data = np.asarray(data)
labels = np.asarray(labels)
yield data, labels # Here data will be mixed datatype arrays & lables will be a float dtype array
i = i + 1
#getting list of files inside the directory
train_file_list = np.sort(glob.glob('././data/train/*.csv'))
test_file_list = np.sort(glob.glob('././data/test/*.csv'))
val_file_list = np.sort(glob.glob('././data/val/*.csv'))
train_dataset = tf.data.Dataset.from_generator(data_generator,args= [train_file_list , batch_size = 2],
output_types = (tf.float32, tf.float32), #This is where I am struck
#my sample data and lables will be like this
data = ['a','b',1,2,3.14,2] #Mixed dtypes
lables = [1.0] #float
)
val_dataset = tf.data.Dataset.from_generator(data_generator,args= [val_file_list , batch_size = 2],
output_types = (tf.float32, tf.float32), #This is where I am struck
)
# Pre processing Part:
def encode_inputs(EMBEDDING_FEATURES,INDICATOR_FEATURES):
''' Function for encoding the deatures'''
encoded_features = []
for feature_name in EMBEDDING_FEATURES:
#Getting unique vocab list
vocabulary = np.array(list(flatten(vocab_list[feature_name])))
# categorical columns using the lists created above:
cat_col = tf.feature_column.categorical_column_with_vocabulary_list(
feature_name, vocabulary)
embedding_dims = int(math.sqrt(len(vocabulary)))
# create an embedding from the categorical column:
cat_emb = tf.feature_column.embedding_column(cat_col,8) #,dimension=embedding_dims
# add the embeddings to the list of feature columns
encoded_features.append(cat_emb)
for feature_name in INDICATOR_FEATURES:
#Getting unique vocab list
vocabulary = list(flatten(vocab_list[feature_name]))
# indicator columns using the lists created above:
ind_col = tf.feature_column.categorical_column_with_vocabulary_list(
feature_name, vocabulary)
# create an embedding from the categorical column:
cat_one_hot = tf.feature_column.indicator_column(ind_col)
# add the embeddings to the list of feature columns
encoded_features.append(cat_one_hot)
# create the input layer for the model
feature_layer = tf.keras.layers.DenseFeatures(encoded_features)
return feature_layer
# Opening JSON file that contains vocab list for str cols
f = open('./vocab_list.json') # File that contains the unique values of each feature
vocab_list = json.load(f)
features_layer = encode_inputs(EMBEDDING_FEATURES,INDICATOR_FEATURES)
# Model Part
model = tf.keras.models.Sequential([
features_layer,
tf.keras.layers.Dense(30, activation = 'relu'),
tf.keras.layers.Dense(1)
])
m_loss = tf.keras.losses.mean_squared_error
m_optimizer = tf.keras.optimizers.SGD(lr = 1e-3)
batch_size = 32
model.compile(loss = m_loss, optimizer = m_optimizer, metrics = ['accuracy'])
model.fit(train_dataset ,epochs = 10, validation_data = val_dataset )