napsternxg

"""Faster Implementation of Unsupervised Query Segmentation.

Uses vectorized operations

- author: @napsternxg

Unsupervised Query Segmentation Using only Query Logs [Mishra et. al. 2011]

https://www.microsoft.com/en-us/research/wp-content/uploads/2011/01/pp0295-mishra.pdf

napsternxg

from flask import Flask, jsonify, request, render_template

from queued_map import example_items
  
app = Flask(__name__)

@app.get("/")
@app.get("/<int:n>")
def home(n: int=10):
    output = example_items(n)

napsternxg

import asyncio

def async_decorator(acreate_fn):
    async def _f(*args, **kwargs):
        print(f"Decorated fn: {args=}, {kwargs=}. Sleeping.")
        await asyncio.sleep(0.1)
        return await acreate_fn(*args, **kwargs)
    return _f

napsternxg

from copy import deepcopy
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from scipy import sparse

from joblib import dump, load
import joblib
import time

napsternxg

mkdir food.com
cd food.com
wget https://www.food.com/sitemap.xml
for url in $(cat sitemap.xml | grep "<loc>https://www.food.com/sitemap-" | sed -n 's:.*<loc>\(.*\)</loc>.*:\1:p');
do echo "Download: $url"; 
done

for url in $(cat sitemap.xml | grep "<loc>https://www.food.com/sitemap-" | sed -n 's:.*<loc>\(.*\)</loc>.*:\1:p');
do wget "$url"; 
done

napsternxg

from pathlib import Path

import torch
from transformers import CLIPProcessor, CLIPTextModelWithProjection
from accelerate import Accelerator
from datasets import Dataset

import pandas as pd
import numpy as np

napsternxg

"""
pip install pypdf
"""

from pypdf import PdfWriter

def main(args):
  merger = PdfWriter()
  file_paths = args.input_files
  for pdf in file_paths:

napsternxg

Awesome Movies Compare

A Pen by Shubhanshu Mishra on CodePen.

License.

napsternxg

diff --git a/sentence_transformers/SentenceTransformer.py b/sentence_transformers/SentenceTransformer.py
index e44e573..ae4dea4 100644
--- a/sentence_transformers/SentenceTransformer.py
+++ b/sentence_transformers/SentenceTransformer.py
@@ -16,6 +16,7 @@ from torch.optim import Optimizer
 from torch.utils.data import DataLoader
 import torch.multiprocessing as mp
 from tqdm.autonotebook import trange
+from tqdm.autonotebook import tqdm
 import math

napsternxg

"""Spacy Embedding Transformer for Sklearn pipeline

Install spacy and floret

```bash
pip install spacy floret scikit-learn
```

First download the vectors from:
```bash