jonas/nlp-lab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update 'Project/naive_approach/README.md'

Browse Source
This commit is contained in:
Jonas Weinz 2018-07-27 13:14:58 +00:00
parent 725980ba58
commit 14960949b3
1 changed files with 22 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
Project/naive_approach/README.md
View File

@ -1,29 +1,29 @@
# naive_approach # # naive_approach
This directory contains the functions necessary to run the Naive Approach. This directory contains the functions necessary to run the Naive Approach.
Prerequisites: Prerequisites:
# the file "emoji_descriptions_preprocessed.csv" has to be located in the specified folder ("../Tools") * the file [emoji_descriptions_preprocessed.csv](../Tools/emoji_descriptions_preprocessed.csv) has to be located in the specified folder [../Tools](../Tools)
# pandas has to be installed * pandas has to be installed
For testing, import naive_approach.py and execute the following commands: For testing, import [naive_approach.py](naive_approach.py) and execute the following commands:
1. prepareData(stem, lower) 1. `prepareData(stem, lower)`
# preprocesses the emoji descriptions and returns a dictionary with the indexed emojis * preprocesses the emoji descriptions and returns a dictionary with the indexed emojis
# parameters: * parameters:
# stem: Apply stemming (default=True) * `stem`: Apply stemming (default=`True`)
# lower: Apply lowercasing (default=True) * `lower`: Apply lowercasing (default=`True`)
2. predict(sentence, lookup, emojis_to_consider, criteria, lang, embeddings, n=10, t=0.9) 2. `predict(sentence, lookup, emojis_to_consider, criteria, lang, embeddings, n=10, t=0.9)`
# evaluates an input sentence and returns a list of predicted emojis * evaluates an input sentence and returns a list of predicted emojis
# parameters: * parameters:
# sentence: Input sentence (required parameter) * `sentence`: Input sentence (required parameter)
# lookup: dictionary with emoji data (return value of prepareData, required parameter) * `lookup`: dictionary with emoji data (return value of prepareData, required parameter)
# emojis_to_consider: set of emojis to include in prediction, or "all" (default="all") * `emojis_to_consider`: set of emojis to include in prediction, or `"all"` (default=`"all"`)
# criteria: criteria to evaluate the values of the description - message matching. * `criteria`: criteria to evaluate the values of the description - message matching.
# options: "sum", "mean", "max_val", "threshold" (default: "threshold") * options: `"sum"`, `"mean"`, `"max_val"`, `"threshold"` (default: `"threshold"`)
# lang: language to use (default: "eng") * `lang`: language to use (default: "eng")
# embeddings: word embeddings * `embeddings`: word embeddings
# options: "wordnet", "word2Vec", "fastText", default: "wordnet" * options: `"wordnet"`, `"word2Vec"`, `"fastText"`, default: `"wordnet"`
# n: number of top ranked emojis to return (default=10) * `n`: number of top ranked emojis to return (default=`10`)
# t: threshold for the "threshold" criteria (default=0.9) * `t`: threshold for the `"threshold"` criteria (default=`0.9`)