$!$pip install lda

$!$pip install "tmtoolkit$[$recommended$]"$

from tmtoolkit.corpus import Corpus, lemmatize, to$\_$lowercase, remove$\_$chars, filter$\_$clean$\_$tokens

from tmtoolkit.corpus import corpus$\_$num$\_$tokens, corpus$\_$tokens$\_$flattened

from tmtoolkit.corpus import dtm

from tmtoolkit.corpus import vocabulary

from tmtoolkit.topicmod.model$\_$io import print$\_$ldamodel$\_$topic$\_$words

from tmtoolkit.topicmod.tm$\_$lda import compute$\_$models$\_$parallel

from string import punctuation

def build$\_$corpus$($texts$,$ lang$="$en$")$:

$"""$Corpus builder which returns a Corpus object processed on texts as language

specified by lang $($defaults to $"$en$")$:

Should perform all of the following pre$-$processing functions:

$-$ Lemmatize the tokens

$-$ Convert tokens to lowercase

$-$ Remove punctuation

$-$ Remove numbers

$-$ Remove tokens shorter than $2$ characters

$"""$

# Here, we just use the index of the text as the label for the corpus item

corpus $=$ Corpus$(\{$ i:r for i$,$ r in enumerate$($texts$)\},$ language$=$lang$)$

# TODO: Complete the implementation of this function and submit the

# $.$py download of this notebook as your assignment submission.