from imodelsx import explain_dataset_iprompt, get_add_two_numbers_dataset

# get a simple dataset of adding two numbers
input_strings, output_strings = get_add_two_numbers_dataset(num_examples=100)
for i in range(5):
    print(repr(input_strings[i]), repr(output_strings[i]))

# explain the relationship between the inputs and outputs
# with a natural-language prompt string
prompts, metadata = explain_dataset_iprompt(
    input_strings=input_strings,
    output_strings=output_strings,
    checkpoint='EleutherAI/gpt-j-6B', # which language model to use
    num_learned_tokens=3, # how long of a prompt to learn
    n_shots=3, # shots per example
    n_epochs=15, # how many epochs to search
    verbose=0, # how much to print
    llm_float16=True, # whether to load the model in float_16
)
--------
prompts is a list of found natural-language prompt strings

from imodelsx import explain_dataset_d3
hypotheses, hypothesis_scores = explain_dataset_d3(
    pos=positive_samples, # List[str] of positive examples
    neg=negative_samples, # another List[str]
    num_steps=100,
    num_folds=2,
    batch_size=64,
)

from imodelsx import AugGAMClassifier, AugTreeClassifier, AugGAMRegressor, AugTreeRegressor
import datasets
import numpy as np

# set up data
dset = datasets.load_dataset('rotten_tomatoes')['train']
dset = dset.select(np.random.choice(len(dset), size=300, replace=False))
dset_val = datasets.load_dataset('rotten_tomatoes')['validation']
dset_val = dset_val.select(np.random.choice(len(dset_val), size=300, replace=False))

# fit model
m = AugGAMClassifier(
    checkpoint='textattack/distilbert-base-uncased-rotten-tomatoes',
    ngrams=2, # use bigrams
)
m.fit(dset['text'], dset['label'])

# predict
preds = m.predict(dset_val['text'])
print('acc_val', np.mean(preds == dset_val['label']))

# interpret
print('Total ngram coefficients: ', len(m.coefs_dict_))
print('Most positive ngrams')
for k, v in sorted(m.coefs_dict_.items(), key=lambda item: item[1], reverse=True)[:8]:
    print('\t', k, round(v, 2))
print('Most negative ngrams')
for k, v in sorted(m.coefs_dict_.items(), key=lambda item: item[1])[:8]:
    print('\t', k, round(v, 2))

from imodelsx import LinearFinetuneClassifier
# fit a simple one-layer finetune
m = LinearFinetuneClassifier(
    checkpoint='distilbert-base-uncased',
)
m.fit(dset['text'], dset['label'])
preds = m.predict(dset_val['text'])
acc = (preds == dset_val['label']).mean()
print('validation acc', acc)

from imodelsx import explain_module_sasc
# a toy module that responds to the length of a string
mod = lambda str_list: np.array([len(s) for s in str_list])

# a toy dataset where the longest strings are animals
text_str_list = ["red", "blue", "x", "1", "2", "hippopotamus", "elephant", "rhinoceros"]
explanation_dict = explain_module_sasc(
    text_str_list,
    mod,
    ngrams=1,
)