-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
1 addition
and
84 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,86 +1,3 @@ | ||
| import spacy | ||
|
|
||
| # ---------------- Pre-processing --------------- | ||
| #https://pyspellchecker.readthedocs.io/en/latest/ | ||
|
|
||
| # from spellchecker import SpellChecker | ||
|
|
||
| # spell = SpellChecker() | ||
|
|
||
| # def correct_text(text): | ||
| # corrected_text = [] | ||
| # phrase = text.split() | ||
| # for word in phrase: | ||
| # print(word) | ||
| # corrected_word = spell.correction(word) | ||
| # print(corrected_word) | ||
| # corrected_text.append(corrected_word) | ||
| # return " ".join(corrected_text) | ||
|
|
||
| # #testing | ||
| # phrase = "hell my neme is Rita. I am portgese" | ||
| # print(correct_text(phrase)) | ||
|
|
||
| # ------------------ Correct words according to context -------- | ||
|
|
||
| # import sparknlp | ||
|
|
||
| # spark = sparknlp.start() | ||
|
|
||
| # from sparknlp.base import * | ||
| # from sparknlp.annotator import * | ||
| # from sparknlp.common import * | ||
| # from pyspark.ml import Pipeline | ||
| # import pandas as pd | ||
|
|
||
| # documentAssembler = DocumentAssembler()\ | ||
| # .setInputCol("text")\ | ||
| # .setOutputCol("document") | ||
|
|
||
| # tokenizer = RecursiveTokenizer()\ | ||
| # .setInputCols(["document"])\ | ||
| # .setOutputCol("token")\ | ||
| # .setPrefixes(["\"", "(", "[", "\n"])\ | ||
| # .setSuffixes([".", ",", "?", ")","!", "'s"]) | ||
|
|
||
| # spellModel = ContextSpellCheckerModel\ | ||
| # .pretrained('spellcheck_dl')\ | ||
| # .setInputCols("token")\ | ||
| # .setOutputCol("checked")\ | ||
| # .setErrorThreshold(4.0)\ | ||
| # .setTradeoff(6.0) | ||
|
|
||
| # finisher = Finisher()\ | ||
| # .setInputCols("checked") | ||
|
|
||
| # pipeline = Pipeline(stages = [ | ||
| # documentAssembler, | ||
| # tokenizer, | ||
| # spellModel, | ||
| # finisher]) | ||
|
|
||
| # empty_ds = spark.createDataFrame([[""]]).toDF("text") | ||
| # lp = LightPipeline(pipeline.fit(empty_ds)) | ||
|
|
||
| # lp.annotate("Please alliow me tao introdduce myhell, I am a man of waelth und tiasted") | ||
|
|
||
|
|
||
|
|
||
|
|
||
| # ------------------ NLP ------------------------ | ||
|
|
||
| #https://spacy.io/usage/spacy-101 | ||
|
|
||
| nlp = spacy.load("en_core_web_sm") | ||
|
|
||
| def answer_generate(user_input): | ||
| doc = nlp(user_input) | ||
|
|
||
| for token in doc: | ||
| #print(token.text, token.pos_, token.dep_) | ||
| if token.text.lower() in ("hello"): | ||
| print("Hi there!") | ||
|
|
||
|
|
||
| answer_generate("Apple is looking at buying U.K. startup for $1 billion") | ||
| answer_generate("Hello there! My name is Rita") | ||
| #TODO: Naïve Bayes Classifier |