datancoffee

<?xml version="1.0" encoding="UTF-8"?>
<jwnl_properties language="en">
    <version publisher="Princeton" number="3.1" language="en"/>
    <dictionary class="net.sf.extjwnl.dictionary.FileBackedDictionary">
        <param name="morphological_processor" value="net.sf.extjwnl.dictionary.morph.DefaultMorphologicalProcessor">
            <param name="operations">
                <param value="net.sf.extjwnl.dictionary.morph.LookupExceptionsOperation"/>
                <param value="net.sf.extjwnl.dictionary.morph.DetachSuffixesOperation">
                    <param name="noun" value="|s=|ses=s|xes=x|zes=z|ches=ch|shes=sh|men=man|ies=y|"/>
                    <param name="verb" value="|s=|ies=y|es=e|es=|ed=e|ed=|ing=e|ing=|"/>

datancoffee

INSERT INTO opinions.stattopic (SnapshotDateId, Topic, Tags, TagCount, cntOrigPublishers, cntRepostWRs,
  cntPositives, cntNegatives, cntAmbiguous, cntGeneral, SentimentHashes, OrigWebResourceHashes, RepostWebResourceHashes )
WITH 
p AS (
 SELECT 20170630 AS SnapshotDateId
),
CalcStatSentiments AS (
  SELECT p.SnapshotDateId, t.Tag, t.GoodAsTopic, d.DocumentHash AS DocumentHash, s.SentimentHash,
    wrOrig.WebResourceHash AS OrigWebResourceHash, wrOrig.Domain AS OrigDomain, wrRepost.WebResourceHash AS RepostWebResourceHash,
    s.DominantValence AS Valence, d.PublicationTime AS PublicationTime

datancoffee

INSERT INTO opinions.stattopic (SnapshotDateId, Topic, Tags, TagCount, cntOrigPublishers, cntRepostWRs,
  cntPositives, cntNegatives, cntAmbiguous, cntGeneral, SentimentHashes, OrigWebResourceHashes, RepostWebResourceHashes )
WITH 
p AS (
 SELECT 20170630 AS SnapshotDateId
),
SentimentTags AS (
  SELECT p.SnapshotDateId, s.SentimentHash, t.Tag, t.GoodAsTopic, s.Tags AS Tags
  FROM p, opinions.sentiment s, UNNEST(s.Tags) AS t
  WHERE

datancoffee

from core.inference.huggingface import InferWithHuggingface
from core.readers.github import ReadGithubIssue
from core.inference.llama3instruct import InferWithLlama3Instruct
from core.transforms.github import GithubIssueToChat
from core.writers.dlt import WriteFile
import os

# Get the Huggingface token
HF_TOKEN = os.getenv("HF_TOKEN")

datancoffee

from transformers import pipeline as hf_pipeline
from typing import Any

from core.actions import Action

class InferWithHuggingface(Action):

    def __init__(
            self,
            actionname: str = None,

datancoffee

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
from typing import Any
from core.actions import Action

class InferWithLlama3Instruct(Action):

    def __init__(
            self,
            hf_token: str,

datancoffee

import dlt
from dlt.common.typing import TDataItems
from dlt.common.schema import TTableSchema
from dlt.common.destination import Destination
from typing import Any
from core.actions import Action

class Read(Action):

    def __init__(self, actionname: str = None):

datancoffee

from core.readers.dlt import Read
import dlt
from dlt.sources.helpers import requests
from typing import Any, Dict, Optional, List


class ReadGithub(Read):

    def __init__(self, actionname:str = None):
        super().__init__(actionname)

datancoffee

from typing import Any, List
from core.actions import Action

class GithubIssueToChat(Action):

    def __init__(self, actionname: str = None):
        super().__init__(actionname)

    def do(self, issues:List, comments:List, *args:Any, **kwargs: Any) -> List:

datancoffee

import dlt
from typing import Any

from dlt.extract import DltResource
from dlt.destinations import filesystem
from core.actions import Action


class WriteFile(Action):