WillKoehrsen

import json
from multiprocessing.dummy import Pool as Threadpool
from itertools import chain

def read_data(file_path):
    """Read in json data from `file_path`"""
    
    data = []
    
    # Open the file and load in json

WillKoehrsen

def process_article(title, text, timestamp, template = 'Infobox book'):
    """Process a wikipedia article looking for template"""
    
    # Create a parsing object
    wikicode = mwparserfromhell.parse(text)
    
    # Search through templates for the template
    matches = wikicode.filter_templates(matches = template)
    
    if len(matches) >= 1:

WillKoehrsen

import xml.sax

class WikiXmlHandler(xml.sax.handler.ContentHandler):
    """Content handler for Wiki XML data using SAX"""
    def __init__(self):
        xml.sax.handler.ContentHandler.__init__(self)
        self._buffer = None
        self._values = {}
        self._current_tag = None
        self._pages = []

WillKoehrsen

C:\Users\willk\OneDrive\Documents\willkoehrsen.github.io\_posts>python medium_to_markdown.py
Enter post url: https://medium.com/@williamkoehrsen/five-minutes-to-your-own-website-fd0b43cbd886
Enter date (as 2018-10-05): 2018-09-16
Post saved as markdown to 2018-09-16-five-minutes-to-your-own-website.md

WillKoehrsen

const mediumToMarkdown = require('medium-to-markdown');
 
// Enter url here
mediumToMarkdown.convertFromUrl('<medium post url>')
.then(function (markdown) {
  console.log(markdown); //=> Markdown content of medium post
});

WillKoehrsen

from sklearn.metrics import roc_auc_score

# Calculate roc auc
roc_value = roc_auc_score(test_labels, rf_probs)

WillKoehrsen

# Actual class predictions
rf_predictions = model.predict(test)
# Probabilities for each class
rf_probs = model.predict_proba(test)[:, 1]

WillKoehrsen

print(f'Model Accuracy: {tree.score(X, y)}')

Model Accuracy: 1.0

WillKoehrsen

from sklearn.ensemble import RandomForestClassifier

# Create the model with 100 trees
model = RandomForestClassifier(n_estimators=100, 
                               bootstrap = True,
                               max_features = 'sqrt')
# Fit on training data
model.fit(train, train_labels)

WillKoehrsen

from sklearn.tree import DecisionTreeClassifier

# Make a decision tree and train
tree = DecisionTreeClassifier(random_state=RSEED)
tree.fit(X, y)