rjurney

{
    "permissions": {
        "allow": [
            "Bash(git status:*)",
            "Bash(git diff:*)",
            "Bash(git log:*)",
            "Bash(poetry update:*)",
            "Bash(pip show:*)",
            "Bash(pip freeze:*)",
            "Bash(pip list:*)",

rjurney

class Solution:
    openers = ["(", "{", "["]
    closers = [")", "}", "]"]
    valid = openers + closers

    def __init__(self):
        self.stack = []

    def push(self, x):
        self.stack.append(x)

rjurney

from collections import defaultdict
from pprint import pprint


class Solution:
    def longestCommonPrefix(self, strs: List[str]) -> str:
        str_count = len(strs)
        min_len = min([len(s) for s in strs])
        print(f"Minimum string length: {min_len:,}")

rjurney

from graphframes.lib import AggregateMessages as AM
from graphframes.examples import Graphs
from pyspark.sql.functions import sum as sqlsum


g = Graphs(spark).friends()  # Get example graph

# For each user, sum the ages of the adjacent users
msgToSrc = AM.dst["age"]
msgToDst = AM.src["age"]

rjurney

import os
import glob
import shutil
import uuid
from pyspark.sql.readwriter import DataFrameWriter


def csv_single(self, path, **options):
    """
    Write the DataFrame as a single CSV file at the specified path.

rjurney

"""Script that tests and times Relik's relation extraction and entity linking on the GraphFrames Paper: https://people.eecs.berkeley.edu/~matei/papers/2016/grades_graphframes.pdf"""

import timeit
import warnings
from pprint import pprint
from relik import Relik  # type: ignore
from relik.inference.data.objects import RelikOutput  # type: ignore

# Squash Relik's warnings for prettier screenshots
warnings.simplefilter("ignore")

rjurney

from pypdf import PdfReader

# Load the PDF. The GraphFrames paper normally resides at 
# https://people.eecs.berkeley.edu/~matei/papers/2016/grades_graphframes.pdf
reader = PdfReader("data/grades_graphframes.pdf")

# Extract text from all pages
text = "\n".join([page.extract_text() for page in reader.pages if page.extract_text()])

# Write it to a text file

rjurney

You can see it linked many topics that are related - Apache Phoenix - but not actually mentioned in the text...

rjurney

Prompt: Find all instances of files containing the term 'motif' or 'graphlet' in this folder 
or any below it. List the filenames, then print the total count of unique files.

rjurney

I can't figure out why this unit test is failing with this error:

> [error] Uncaught exception when running org.graphframes.lib.ConnectedComponentsSuite: java.lang.OutOfMemoryError: Java 
heap space sbt.ForkMain$ForkError: java.lang.OutOfMemoryError: Java heap space

The test is an 8 node, 6 edge graph of two components and two dangling vertices. WTF heap space? I cleaned up the `Dockerfile`
below because it was on wonky versions and tried the same commands there... no go. Same exception. The weird thing is that 
CI does pass these tests... so I don't get what is going wrong.

HOW YOU CAN HELP: Please run this command and tell me if the tests pass: