add progress and better scraping.

This commit is contained in:
matt 2023-04-22 13:00:24 -07:00
parent 297aeec32d
commit d43ed4658a
7 changed files with 287 additions and 73 deletions

1
.gitignore vendored
View File

@ -1,3 +1,4 @@
*.csv *.csv
*.swp *.swp
__pycache__ __pycache__
tmp.py

View File

@ -1,31 +1,39 @@
# Data Mining - CSCI 577 # Data Mining - CSCI 577
# Project Status Report I # Project Status Report III
*2023-04-04* *2023-04-18*
## Participants ## Participants
Matt Jensen Matt Jensen
## Overarching Purpose Computer Science 477/577
Project Status Report III
Due: Tuesday, April 18
I hope to use a dataset of new articles to track the polarization of news over time. ## Tools
I have a hypothesis that news has become more polarized superficially, but has actually converged into only two dominate views points.
I think there is a connection to be made to other statistics, like voting polarity in congress, or income inequality, or consolidation of media into the hands of the few.
## Data Source > The third project progress report should include a preliminary account of the existing software tools you will be using.
> Ideally, you obtain the software you will (probably) need and run it on sample files (or your real files), so make sure that you understand how they work.
> Do not wait verify that there are no hidden complications.
> The are many plausible sources for such software, including the following:
To test this thesis, I will crawl the archives of [memeorandum.com](https://www.memeorandum.com/) for news stories from 2006 onward. I will use the following suite of python tools to conduct my research:
I will grab the title, author, publisher, published date, url and related discussions and store it in a .csv.
The site also has a concept of references, where a main, popular story may be covered by other sources.
So there is a concept of link similarity that could be explored in this analysis too.
## Techniques - python
- pytorch
- scikit-learn
- duckdb
- requests
- pandas
- matplotlib
- seaborn
I am unsure of which technique specifically will work best, but I believe an unsupervised clustering algorithm will serve me well. ## Purpose
I think there is a way to test the ideal number of clusters should exist to minimize the error.
This could be a good proxy for how many 'viewpoints' are allowed in 'mainstream' news media. > This progress should also provide a definitive description of your purpose and how you intend to conduct it.
> This should take the form of a detailed outline of the procedures you will undertake in exploring your dataset(s) and maximizing the knowledge that can be extracted from it.
\newpage \newpage
@ -103,3 +111,31 @@ Another goal is to look at the political alignment over time.
I will train a classifier to predict political bias based on the word embeddings as well. I will train a classifier to predict political bias based on the word embeddings as well.
There is a concept of the [Overton Window](https://en.wikipedia.org/wiki/Overton_window) and I would be curious to know if title of new articles could be a proxy for the location of the overton window over time. There is a concept of the [Overton Window](https://en.wikipedia.org/wiki/Overton_window) and I would be curious to know if title of new articles could be a proxy for the location of the overton window over time.
\newpage
# Project Status Report I
*2023-04-04*
## Participants
Matt Jensen
## Overarching Purpose
I hope to use a dataset of new articles to track the polarization of news over time.
I have a hypothesis that news has become more polarized superficially, but has actually converged into only two dominate views points.
I think there is a connection to be made to other statistics, like voting polarity in congress, or income inequality, or consolidation of media into the hands of the few.
## Data Source
To test this thesis, I will crawl the archives of [memeorandum.com](https://www.memeorandum.com/) for news stories from 2006 onward.
I will grab the title, author, publisher, published date, url and related discussions and store it in a .csv.
The site also has a concept of references, where a main, popular story may be covered by other sources.
So there is a concept of link similarity that could be explored in this analysis too.
## Techniques
I am unsure of which technique specifically will work best, but I believe an unsupervised clustering algorithm will serve me well.
I think there is a way to test the ideal number of clusters should exist to minimize the error.
This could be a good proxy for how many 'viewpoints' are allowed in 'mainstream' news media.

BIN
docs/progress_spec_3.docx Normal file

Binary file not shown.

180
src/bias.py Normal file
View File

@ -0,0 +1,180 @@
import click
from data import connect
import pandas as pd
from lxml import etree
from pathlib import Path
import os
import csv
@click.group()
def cli() -> None:
...
def map(rating:str) -> int:
mapping = {
'right' : 0,
'left-center' : 1,
'center' : 2,
'left' : 3,
'allsides' : 4,
'right-center' : 5
}
return mapping[rating]
@cli.command()
def load() -> None:
DB = connect()
DATA_DIR = Path(os.environ['DATA_MINING_DATA_DIR'])
f = str(DATA_DIR / "bias_ratings.csv")
DB.sql(f"""
create table bias_ratings as
select
row_number() over(order by b.publisher) as id
,b.*
from read_csv_auto('{f}') b
""")
@cli.command()
def join() -> None:
DB = connect()
DB.sql("""
with cte as (
select
s.publisher
,count(1) as stories
from stories s
group by s.publisher
)
select
s.publisher
,s.stories
,b.publisher
,b.bias
from bias_ratings b
join cte s
on s.publisher = b.publisher
order by
stories desc
limit 15
""")
DB.sql("""
with cte as (
select
s.publisher
,count(1) as stories
from stories s
group by s.publisher
)
select
sum(stories)
,avg(agree / disagree)
from bias_ratings b
join cte s
on s.publisher = b.publisher
""")
DB.sql("""
with cte as (
select
s.publisher
,count(1) as stories
from stories s
group by s.publisher
)
select
sum(s.stories) filter(where b.publisher is not null) as matched
,sum(s.stories) filter(where b.publisher is null) as unmatched
,cast(sum(s.stories) filter(where b.publisher is not null) as numeric)
/ sum(s.stories) filter(where b.publisher is null) as precent_matched
from bias_ratings b
right join cte s
on s.publisher = b.publisher
""")
DB.sql("""
select
*
from bias_ratings
where publisher ilike '%CNN%'
""")
@cli.command()
def debug() -> None:
DB = connect()
DATA_DIR = Path(os.environ['DATA_MINING_DATA_DIR'])
f = str(DATA_DIR / "bias_ratings.csv")
DB.sql("""
with cte as (
select
outlet
,count(1) as stories
from stories
group by outlet
)
,total as (
select
sum(stories) as total
from cte
)
select
cte.outlet
,cte.stories
,bias.outlet
,bias.lean
,sum(100 * (cte.stories / cast(total.total as float))) over() as rep
,total.total
from cte
join bias
on jaro_winkler_similarity(bias.outlet, cte.outlet) > 0.9
cross join total.total
""")
DB.sql("""
select
outlet
,count(1) as stories
from stories
group by outlet
order by count(1) desc
limit 50
""")
outlets
@cli.command()
def parse_html() -> None:
"""parse the save html page of allslides.com bias ratings into a normalized csv file"""
DB = connect()
DATA_DIR = Path(os.environ['DATA_MINING_DATA_DIR'])
bias_html = DATA_DIR / 'allsides.html'
parser = etree.HTMLParser()
tree = etree.parse(str(bias_html), parser)
root = tree.getroot()
rows = root.xpath('//table[contains(@class,"views-table")]/tbody/tr')
ratings = []
for row in rows:
rating = dict()
publisher = row.xpath('./td[contains(@class, "source-title")]/a')[0].text
rating['publisher'] = publisher
bias = row.xpath('./td[contains(@class, "views-field-field-bias-image")]/a')[0].get('href')
bias = bias.split('/')[-1]
rating['bias'] = bias
agree = row.xpath('.//span[contains(@class, "agree")]')[0].text
disagree = row.xpath('.//span[contains(@class, "disagree")]')[0].text
rating['agree'] = int(agree)
rating['disagree'] = int(disagree)
ratings.append(rating)
df = pd.DataFrame(ratings)
df.to_csv(DATA_DIR / 'bias_ratings.csv', sep="|", index=False, quoting=csv.QUOTE_NONNUMERIC)
if __name__ == "__main__":
cli()

View File

@ -1,46 +0,0 @@
import click
import duckdb
from data import connect
import polars as ps
DB = connect()
DATA_DIR = Path(os.environ['DATA_MINING_DATA_DIR'])
bias = ps.read_csv(DATA_DIR / 'allsides_bias.csv', sep="|")
DB.sql("""
with cte as (
select
outlet
,count(1) as stories
from stories
group by outlet
)
,total as (
select
sum(stories) as total
from cte
)
select
cte.outlet
,cte.stories
,bias.outlet
,bias.lean
,sum(100 * (cte.stories / cast(total.total as float))) over() as rep
,total.total
from cte
join bias
on jaro_winkler_similarity(bias.outlet, cte.outlet) > 0.9
cross join total.total
""")
DB.sql("""
select
outlet
,count(1) as stories
from stories
group by outlet
order by count(1) desc
limit 50
""")
outlets

View File

@ -59,9 +59,10 @@ def download(output_dir):
@cli.command() @cli.command()
@click.option('-d', '--directory', type=Path, default=data_dir() / "memeorandum") @click.option('-d', '--directory', type=Path, default=data_dir() / "memeorandum", show_default=True)
@click.option('-o', '--output_dir', type=Path, default=data_dir()) @click.option('-o', '--output_dir', type=Path, default=data_dir(), show_default=True)
def parse(directory, output_dir): def parse(directory, output_dir):
"""parse the html files on disk into a structured csv format."""
directory = data_dir() / "memeorandum" directory = data_dir() / "memeorandum"
parser = etree.HTMLParser() parser = etree.HTMLParser()
pages = [f for f in directory.glob("*.html")] pages = [f for f in directory.glob("*.html")]
@ -72,14 +73,14 @@ def parse(directory, output_dir):
for page in page_iter: for page in page_iter:
page_iter.set_postfix_str(f"{page}") page_iter.set_postfix_str(f"{page}")
date = datetime.datetime.strptime(page.stem, '%y-%m-%d') date = datetime.datetime.strptime(page.stem, '%y-%m-%d')
# tree = etree.parse(str(page), parser)
tree = etree.parse(str(page), parser) tree = etree.parse(str(page), parser)
root = tree.getroot() root = tree.getroot()
if not root: if root is None:
print(f"error opening {page}") print(f"error opening {page}")
continue continue
items = root.xpath("//div[contains(@class, 'item')]") items = root.xpath("//div[contains(@class, 'item')]")
# item = items[0]
for item in items: for item in items:
out = dict() out = dict()
citation = item.xpath('./cite') citation = item.xpath('./cite')
@ -92,16 +93,24 @@ def parse(directory, output_dir):
author = '' author = ''
out['author'] = author out['author'] = author
try: try:
url = citation[0].getchildren()[0].get('href') publisher_url = citation[0].getchildren()[0].get('href')
publisher = citation[0].getchildren()[0].text publisher = citation[0].getchildren()[0].text
except IndexError as e: except IndexError as e:
print(f"error with citation url: {page}") print(f"error with citation url: {page}")
out['publisher'] = publisher out['publisher'] = publisher
out['publisher_url'] = url out['publisher_url'] = publisher_url
title = item.xpath('.//strong/a')[0].text title = item.xpath('.//strong/a')[0].text
out['title'] = title out['title'] = title
item_id = hash((title,page.stem,url))
url = item.xpath('.//strong/a')[0].get('href')
out['url'] = url
item_id = hash((page.stem, url))
out['id'] = item_id out['id'] = item_id
old_id = hash((title, page.stem, publisher_url))
out['old_id'] = old_id
published.append(out) published.append(out)
related = item.xpath(".//span[contains(@class, 'mls')]/a") related = item.xpath(".//span[contains(@class, 'mls')]/a")
@ -113,9 +122,22 @@ def parse(directory, output_dir):
another['parent_id'] = item_id another['parent_id'] = item_id
others.append(another) others.append(another)
df = pd.DataFrame(published) df = pd.DataFrame(published)
df.to_csv(output_dir / 'stories.csv', sep='|', index=False) df.to_csv(output_dir / 'stories_v2.csv', sep='|', index=False)
df = pd.DataFrame(others) df = pd.DataFrame(others)
df.to_csv(output_dir / 'related.csv', sep='|', index=False) df.to_csv(output_dir / 'related_v2.csv', sep='|', index=False)
@cli.command()
def normalize():
DB = connect()
DB.sql("""
create table publishers as
select
row_number() over(order by publisher) as id
,publisher
,publisher_url
from stories
group by publisher, publisher_url
""")
if __name__ == "__main__": if __name__ == "__main__":

View File

@ -3,28 +3,49 @@ from scipy.spatial import distance
from transformers import AutoTokenizer, RobertaModel from transformers import AutoTokenizer, RobertaModel
import numpy as np import numpy as np
from model import Model from model import Model
from data import Data, from_db from data import Data, from_db, connect
@click.group() @click.group()
def cli(): def cli():
... ...
@cli.command()
def max_sequence():
db = connect()
longest = db.sql("""
select
title
from stories
order by length(title) desc
limit 5000
""").df()
tokenizer = AutoTokenizer.from_pretrained("roberta-base")
tokens = tokenizer(longest['title'].to_list())
print(f"{max([len(x) for x in tokens['input_ids']])}")
@cli.command() @cli.command()
def train(): def train():
table = from_db(Data.Titles) table = from_db(Data.Titles)
n_classes = 10 n_classes = 10
tokenizer = AutoTokenizer.from_pretrained("roberta-base") tokenizer = AutoTokenizer.from_pretrained("roberta-base")
model = RobertaModel.from_pretrained("roberta-base") model = RobertaModel.from_pretrained("roberta-base")
def get_embeddings(titles): def get_embeddings(titles):
# create tokens, padding to max width # create tokens, padding to max width
tokens = tokenizer(titles, add_special_tokens = True, truncation = True, padding = "max_length", return_attention_mask = True, return_tensors = "pt") tokens = tokenizer(titles, add_special_tokens = True, truncation = True, padding = "max_length", max_length=70, return_attention_mask = True, return_tensors = "pt")
outputs = model(**tokens) outputs = model(**tokens)
return outputs.last_hidden_state[:, 0, :] return outputs.last_hidden_state[:, 0, :]
titles = table['title'].apply(str).to_list()[:10] titles = table['title'].apply(str).to_list()[:10]
get_embeddings(titles) get_embeddings(titles)
outputs.last_hidden_state[0][200:]
outputs.values().shape
model
# linear = torch.nn.Linear(model.config.hidden_size, n_classes) # linear = torch.nn.Linear(model.config.hidden_size, n_classes)
# act = torch.nn.Sigmoid() # act = torch.nn.Sigmoid()