from sklearn.model_selection import train_test_split

from nyaggle.experiment import run_experiment
from nyaggle.testing import make_classification_df

X, y = make_classification_df()
X_train, X_test, y_train, y_test = train_test_split(X, y)

params = {
    'n_estimators': 1000,
    'max_depth': 8
}

result = run_experiment(params,
                        X_train,
                        y_train,
                        X_test)

# You can get outputs that needed in data science competitions with 1 API

print(result.test_prediction)  # Test prediction in numpy array
print(result.oof_prediction)   # Out-of-fold prediction in numpy array
print(result.models)           # Trained models for each fold
print(result.importance)       # Feature importance for each fold
print(result.metrics)          # Evalulation metrics for each fold
print(result.time)             # Elapsed time
print(result.submission_df)    # The output dataframe saved as submission.csv

# ...and all outputs have been saved under the logging directory (default: output/yyyymmdd_HHMMSS).


# You can use it with mlflow and track your experiments through mlflow-ui
result = run_experiment(params,
                        X_train,
                        y_train,
                        X_test,
                        with_mlflow=True)

from nyaggle.experiment import Experiment

with Experiment(logging_directory='./output/') as exp:
    # log key-value pair as a parameter
    exp.log_param('lr', 0.01)
    exp.log_param('optimizer', 'adam')

    # log text
    exp.log('blah blah blah')

    # log metric
    exp.log_metric('CV', 0.85)

    # log numpy ndarray, pandas dafaframe and any artifacts
    exp.log_numpy('predicted', predicted)
    exp.log_dataframe('submission', sub, file_format='csv')
    exp.log_artifact('path-to-your-file')

import pandas as pd
import numpy as np

from sklearn.model_selection import KFold
from nyaggle.feature.category_encoder import TargetEncoder


train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
all = pd.concat([train, test]).copy()

cat_cols = [c for c in train.columns if train[c].dtype == np.object]
target_col = 'y'

kf = KFold(5)

# Target encoding with K-fold
te = TargetEncoder(kf.split(train))

# use fit/fit_transform to train data, then apply transform to test data
train.loc[:, cat_cols] = te.fit_transform(train[cat_cols], train[target_col])
test.loc[:, cat_cols] = te.transform(test[cat_cols])

# ... or just call fit_transform to concatenated data
all.loc[:, cat_cols] = te.fit_transform(all[cat_cols], all[cat_cols])

import pandas as pd
from nyaggle.feature.nlp import BertSentenceVectorizer


train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')
all = pd.concat([train, test]).copy()

text_cols = ['body']
target_col = 'y'
group_col = 'user_id'


# extract BERT-based sentence vector
bv = BertSentenceVectorizer(text_columns=text_cols)

text_vector = bv.fit_transform(train)


# BERT + SVD, with cuda
bv = BertSentenceVectorizer(text_columns=text_cols, use_cuda=True, n_components=40)

text_vector_svd = bv.fit_transform(train)

# Japanese BERT
bv = BertSentenceVectorizer(text_columns=text_cols, lang='jp')

japanese_text_vector = bv.fit_transform(train)

import pandas as pd
from nyaggle.validation import adversarial_validate

train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')

auc, importance = adversarial_validate(train, test, importance_type='gain')

import pandas as pd
from sklearn.model_selection import cross_validate, KFold
from nyaggle.validation import TimeSeriesSplit, Take, Skip, Nth

train = pd.read_csv('train.csv', parse_dates='dt')

# time-series split
ts = TimeSeriesSplit(train['dt'])
ts.add_fold(train_interval=('2019-01-01', '2019-01-10'), test_interval=('2019-01-10', '2019-01-20'))
ts.add_fold(train_interval=('2019-01-06', '2019-01-15'), test_interval=('2019-01-15', '2019-01-25'))

cross_validate(..., cv=ts)

# take the first 3 folds out of 10
cross_validate(..., cv=Take(3, KFold(10)))

# skip the first 3 folds, and evaluate the remaining 7 folds
cross_validate(..., cv=Skip(3, KFold(10)))

# evaluate 1st fold
cross_validate(..., cv=Nth(1, ts))