| #!/usr/bin/env python | |
| """Compiles compact FAR from tokenized data for LM construction.""" | |
| import argparse | |
| import collections | |
| import heapq | |
| import logging | |
| import operator | |
| from typing import List |
| #!/usr/bin/env python | |
| """ONE-LINE DESCRIPTION HERE.""" | |
| import argparse | |
| import logging | |
| def main(args): | |
| # ADD LOGIC HERE. |
| #!/usr/bin/env python | |
| # What's the nearest word (in Levenshtein distance) to "covfefe"? | |
| import string | |
| # Available from: https://github.com/kylebgorman/EditTransducer | |
| import edit_transducer | |
| # You probably have this file if you're on Linux or Mac OS X. | |
| with open("/usr/share/dict/words") as source: |
| # On Linux: | |
| sudo ldconfig | |
| # On Mac OS X: | |
| sudo update_dyld_shared_cache |
| """Yeonju's solution to part 1 of MP1.""" | |
| import nltk | |
| text = """du | |
| du hast | |
| du hast mich | |
| du | |
| du hast | |
| du hast mich |
| alias beatblender="mplayer -playlist http://somafm.com/beatblender130.pls" | |
| alias covers="mplayer -playlist http://somafm.com/covers130.pls" | |
| alias deepspaceone="mplayer -playlist http://somafm.com/deepspaceone130.pls" | |
| alias defconradio="mplayer -playlist http://somafm.com/defconradio130.pls" | |
| alias dronezone="mplayer -playlist http://somafm.com/dronezone130.pls" | |
| alias fluid="mplayer -playlist http://somafm.com/fluid130.pls" | |
| alias groovesalad="mplayer -playlist http://somafm.com/groovesalad130.pls" | |
| alias gsclassic="mplayer -playlist http://somafm.com/gsclassic130.pls" | |
| alias indiepoprocks="mplayer -playlist http://somafm.com/indiepoprocks130.pls" | |
| alias lush="mplayer -playlist http://somafm.com/lush130.pls" |
| #!/usr/bin/env python | |
| """Checks that PyTorch can reach CUDA.""" | |
| import sys | |
| import torch | |
| if __name__ == "__main__": | |
| if not torch.cuda.is_available(): |
| """Log-odds computations.""" | |
| from libc.math cimport log, sqrt | |
| from libc.stdint cimport int64_t | |
| ctypedef int64_t int64 | |
In this (optional) MP you will prepare a corpus of free English newswire text for use in later assignments. This is intended to provide practical Python programming experience, but will not be graded.
For this task we will use a subset of the News Crawl corpus consisting of data from the year 2009. This (very large: 3.7 GB) file is available here as a gzipped TAR file.