# Helpers to grab text or image from pandas column.
from embetter.grab import ColumnGrabber

# Representations/Helpers for computer vision
from embetter.vision import ImageLoader, TimmEncoder, ColorHistogramEncoder

# Representations for text
from embetter.text import SentenceEncoder, Sense2VecEncoder, BytePairEncoder, spaCyEncoder

# Finetuning components 
from embetter.finetune import ForwardFinetuner

# External embedding providers, typically needs an API key
from embetter.external import CohereEncoder, OpenAIEncoder

import pandas as pd
from sklearn.linear_model import LogisticRegression

from embetter.grab import ColumnGrabber
from embetter.text import SentenceEncoder

# This pipeline grabs the `text` column from a dataframe
# which then get fed into Sentence-Transformers' all-MiniLM-L6-v2.
text_emb_pipeline = make_pipeline(
  ColumnGrabber("text"),
  SentenceEncoder('all-MiniLM-L6-v2')
)

# This pipeline can also be trained to make predictions, using
# the embedded features. 
text_clf_pipeline = make_pipeline(
  text_emb_pipeline,
  LogisticRegression()
)

dataf = pd.DataFrame({
  "text": ["positive sentiment", "super negative"],
  "label_col": ["pos", "neg"]
})
X = text_emb_pipeline.fit_transform(dataf, dataf['label_col'])
text_clf_pipeline.fit(dataf, dataf['label_col']).predict(dataf)

import pandas as pd
from sklearn.pipeline import make_pipeline 
from sklearn.linear_model import LogisticRegression

from embetter.grab import ColumnGrabber
from embetter.vision import ImageLoader, TimmEncoder

# This pipeline grabs the `img_path` column from a dataframe
# then it grabs the image paths and turns them into `PIL.Image` objects
# which then get fed into MobileNetv2 via TorchImageModels (timm).
image_emb_pipeline = make_pipeline(
  ColumnGrabber("img_path"),
  ImageLoader(convert="RGB"),
  TimmEncoder("mobilenetv2_120d")
)

dataf = pd.DataFrame({
  "img_path": ["tests/data/thiscatdoesnotexist.jpeg"]
})
image_emb_pipeline.fit_transform(dataf)