char_level_lang_model_load_data.py

# Load names
data = open("../data/names.txt", "r").read()

# Convert characters to lower case
data = data.lower()

# Construct vocabulary using unique characters, sort it in ascending order,
# then construct two dictionaries that maps character to index and index to
# characters.
chars = list(sorted(set(data)))
chars_to_idx = {ch:i for i, ch in enumerate(chars)}
idx_to_chars = {i:ch for ch, i in chars_to_idx.items()}

# Get the size of the data and vocab size
data_size = len(data)
vocab_size = len(chars_to_idx)
print(f"There are {data_size} characters and {vocab_size} unique characters.")

# Fitting the model
parameters, loss = model("../data/names.txt", chars_to_idx, idx_to_chars, 100, vocab_size, 100, 0.01)

# Plotting the loss
plt.plot(range(len(loss)), loss)
plt.xlabel("Epochs")
plt.ylabel("Smoothed loss");