Upload 11 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+dis_image.png filter=lfs diff=lfs merge=lfs -text
+transfer_tweet/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

acronym.json

@@ -0,0 +1 @@
+{"aka":"also known as","asap":"as soon as possible","brb":"be right back","btw":"by the way","dob":"date of birth","faq":"frequently asked questions","fyi":"for your information","idk":"i don't know","idc":"i don't care","iirc":"if i recall correctly","imo":"in my opinion","irl":"in real life","lmk":"let me know","lol":"laugh out loud","ngl":"not gonna lie","noyb":"none of your business","nvm":"never mind","ofc":"of course","omg":"oh my god","pfa":"please find attached","rofl":"rolling on the floor laughing","stfu":"shut the fuck up","tba":"to be announced","tbc":"to be continued","tbd":"to be determined","tbh":"to be honest","ttyl":"talk to you later","wtf":"what the fuck","wth":"what the heck"}

app.py

@@ -0,0 +1,146 @@
+# importing Libraries
+
+import streamlit as st
+import PIL
+from PIL import Image
+import tensorflow as tf
+from nltk.stem import WordNetLemmatizer
+from nltk.tokenize import RegexpTokenizer
+import re
+import string
+import numpy as np
+import pandas as pd
+import nltk
+
+try:                                                                         # Check if wordnet is installed
+    nltk.find("corpora/wordnet.zip")          
+except LookupError:
+    nltk.download('wordnet')
+
+# ----------------------------------------------------------------------------------
+# read files
+try:
+    acronyms_dict, contractions_dict, stops
+except NameError:
+    acronyms_dict = pd.read_json("acronym.json", typ = "series")
+    contractions_dict = pd.read_json("contractions.json", typ = "series")
+    stops = list(pd.read_csv('stopwords.csv').values.flatten())
+
+# ----------------------------------------------------------------------------------
+# Defining tokenizer
+regexp = RegexpTokenizer("[\w']+")
+
+# preprocess Function
+def preprocess(text):
+    
+    text = text.lower()                                                                                        # lowercase
+    text = text.strip()                                                                                        # whitespaces
+    
+    # Removing html tags
+    html = re.compile(r'<.*?>')
+    text = html.sub(r'', text)                                                                                 # html tags
+    
+    # Removing emoji patterns
+    emoji_pattern = re.compile("["
+                           u"\U0001F600-\U0001F64F"  # emoticons
+                           u"\U0001F300-\U0001F5FF"  # symbols & pictographs
+                           u"\U0001F680-\U0001F6FF"  # transport & map symbols
+                           u"\U0001F1E0-\U0001F1FF"  # flags (iOS)
+                           u"\U00002702-\U000027B0"
+                           u"\U000024C2-\U0001F251"
+                           "]+", flags = re.UNICODE)
+    text = emoji_pattern.sub(r'', text)                                                                         # unicode char
+    
+    # Removing urls
+    http = "https?://\S+|www\.\S+" # matching strings beginning with http (but not just "http")
+    pattern = r"({})".format(http) # creating pattern
+    text = re.sub(pattern, "", text)                                                                            # remove urls
+    
+    # Removing twitter usernames
+    pattern = r'@[\w_]+'
+    text = re.sub(pattern, "", text)                                                                            # remove @twitter usernames
+    
+    # Removing punctuations and numbers
+    punct_str = string.punctuation + string.digits
+    punct_str = punct_str.replace("'", "")
+    punct_str = punct_str.replace("-", "")
+    text = text.translate(str.maketrans('', '', punct_str))                                                     # punctuation and numbers
+    
+    # Replacing "-" in text with empty space
+    text = text.replace("-", " ")                                                                               # "-"
+    
+    # Substituting acronyms
+    words = []
+    for word in regexp.tokenize(text):
+        if word in acronyms_dict.index:
+            words = words + acronyms_dict[word].split()
+        else:
+            words = words + word.split()
+    text = ' '.join(words)                                                                                       # acronyms
+    
+    # Substituting Contractions
+    words = []
+    for word in regexp.tokenize(text):
+        if word in contractions_dict.index:
+            words = words + contractions_dict[word].split()
+        else:
+            words = words + word.split()
+    text = " ".join(words)                                                                                       # contractions
+    
+    punct_str = string.punctuation
+    text = text.translate(str.maketrans('', '', punct_str))                                                     # punctuation again to remove "'"
+    
+    # lemmatization
+    lemmatizer = WordNetLemmatizer()
+    text = " ".join([lemmatizer.lemmatize(word) for word in regexp.tokenize(text)])                             # lemmatize
+    
+    # Stopwords Removal
+    text = ' '.join([word for word in regexp.tokenize(text) if word not in stops])                              # stopwords
+    
+    # Removing all characters except alphabets and " " (space)
+    filter = string.ascii_letters + " "
+    text = "".join([chr for chr in text if chr in filter])                                                      # remove all characters except alphabets and " " (space)
+    
+    # Removing words with one alphabet occuring more than 3 times continuously
+    pattern = r'\b\w*?(.)\1{2,}\w*\b'
+    text = re.sub(pattern, "", text).strip()                                                                    # remove words with one alphabet occuring more than 3 times continuously
+    
+    # Removing words with less than 3 characters
+    short_words = r'\b\w{1,2}\b'
+    text = re.sub(short_words, "", text)                                                                     # remove words with less than 3 characters
+    
+    # return final output
+    return text
+
+# ===============================================================================================================
+                                       # STREAMLIT
+
+# App Devolopment Starts
+st.set_page_config(layout="wide")
+st.write("# Disaster Tweet Predictor")
+
+img = Image.open("dis_image.png")
+st.image(img)
+
+tweet = st.text_input(label = "Enter or paste your tweet here", value = "")
+
+# Defining a function to store the model in streamlit cache memory
+@st.cache_resource
+def cache_model(model_name):
+    model = tf.keras.models.load_model(model_name)
+    return model
+
+model = cache_model("transfer_tweet")
+
+# if user gives any input
+if len(tweet) > 0:
+    clean_tweet = preprocess(tweet)                   # cleans tweet
+    y_pred = model.predict([clean_tweet])             # gives probability of class = 1
+    y_pred_num = int(np.round(y_pred)[0][0])          # get final prediction of output class
+    
+    if y_pred_num == 0:
+        st.write(f"#### Non-Disaster tweet with disaster probability {round(y_pred[0][0]*100, 4)}%")
+    else:
+        st.write(f"#### Disaster tweet with disaster probability {round(y_pred[0][0]*100, 4)}%")
+
+# ==============================================================================================================

contractions.json

@@ -0,0 +1 @@
+{"'aight":"alright","ain't":"are not","amn't":"am not","arencha":"are not you","aren't":"are not","'bout":"about","can't":"cannot","cap'n":"captain","'cause":"because","'cept":"except","could've":"could have","couldn't":"could not","couldn't've":"could not have","dammit":"damn it","daren't":"dare not","daresn't":"dare not","dasn't":"dare not","didn't":"did not","doesn't":"does not","doin'":"doing","don't":"do not","dunno":"do not know","d'ye":"do you","e'en":"even","e'er":"ever","'em":"them","everybody's":"everybody is","everyone's":"everyone is","fo'c'sle":"forecastle","finna":"fixing to","'gainst":"against","g'day":"good day","gimme":"give me","giv'n":"given","gonna":"going to","gon't":"go not","gotcha":"got you","gotta":"got to","gtg":"got to go","hadn't":"had not","had've":"had have","hasn't":"has not","haven't":"have not","he'd":"he had","he'll":"he shall","helluva":"hell of a","he's":"he is","here's":"here is","he've":"he have","how'd":"how would","howdy":"how do you do","how'll":"how will","how're":"how are","how's":"how is","i'd":"i had","i'd've":"i would have","i'll":"i shall","i'm":"i am","imma":"i am about to","i'm'a":"i am about to","i'm'o":"i am going to","innit":"is it not","ion":"i do not","i've":"i have","isn't":"is not","it'd":"it would","it'll":"it shall","it's":"it is","iunno":"i do not know","kinda":"kind of","let's":"let us","li'l":"little","ma'am":"madam","mayn't":"may not","may've":"may have","methinks":"me thinks","mightn't":"might not","might've":"might have","mustn't":"must not","mustn't've":"must not have","must've":"must have","'neath":"beneath","needn't":"need not","nal":"and all","ne'er":"never","o'clock":"of the clock","o'er":"over","ol'":"old","oughtn't":"ought not","'round":"around","'s":"is","shalln't":"shall not","shan't":"shall not","she'd":"she had","she'll":"she shall","she's":"she is","should've":"should have","shouldn't":"should not","shouldn't've":"should not have","somebody's":"somebody is","someone's":"someone is","something's":"something is","so're":"so are","so's":"so is","so've":"so have","that'll":"that shall","that're":"that are","that's":"that is","that'd":"that would","there'd":"there had","there'll":"there shall","there're":"there are","there's":"there is","these're":"these are","these've":"these have","they'd":"they had","they'll":"they shall","they're":"they are","they've":"they have","this's":"this is","those're":"those are","those've":"those have","'thout":"without","'til":"until","'tis":"it is","to've":"to have","'twas":"it was","'tween":"between","'twhere":"it were","wanna":"want to","wasn't":"was not","we'd":"we had","we'd've":"we would have","we'll":"we shall","we're":"we are","we've":"we have","weren't":"were not","whatcha":"what are you","what'd":"what did","what'll":"what shall","what're":"what are","what's":"what is","what've":"what have","when's":"when is","where'd":"where did","where'll":"where shall","where're":"where are","where's":"where is","where've":"where have","which'd":"which had","which'll":"which shall","which're":"which are","which's":"which is","which've":"which have","who'd":"who would","who'd've":"who would have","who'll":"who shall","who're":"who are","who's":"who is","who've":"who have","why'd":"why did","why're":"why are","why's":"why is","willn't":"will not","won't":"will not","wonnot":"will not","would've":"would have","wouldn't":"would not","wouldn't've":"would not have","y'all":"you all","y'all'd've":"you all would have","y'all'd'n't've":"you all would not have","y'all're":"you all are","y'all'ren't":"you all are not","y'at":"you at","yes'm":"yes madam","yessir":"yes sir","you'd":"you had","you'll":"you shall","you're":"you are","you've":"you have","aight":"alright","aint":"are not","amnt":"am not","arent":"are not","cant":"cannot","cause":"because","couldve":"could have","couldnt":"could not","couldntve":"could not have","darent":"dare not","daresnt":"dare not","dasnt":"dare not","didnt":"did not","doesnt":"does not","doin":"doing","dont":"do not","eer":"ever","everybodys":"everybody is","everyones":"everyone is","gday":"good day","givn":"given","gont":"go not","hadnt":"had not","hadve":"had have","hasnt":"has not","havent":"have not","hed":"he had","hell":"he shall","hes":"he is","heve":"he have","howd":"how did","howll":"how will","howre":"how are","hows":"how is","idve":"i would have","ill":"i shall","im":"i am","ima":"i am about to","imo":"i am going to","ive":"i have","isnt":"is not","itd":"it would","itll":"it shall","its":"it is","lets":"let us","lil":"little","maam":"madam","maynt":"may not","mayve":"may have","mightnt":"might not","mightve":"might have","mustnt":"must not","mustntve":"must not have","mustve":"must have","neednt":"need not","neer":"never","oclock":"of the clock","oer":"over","ol":"old","oughtnt":"ought not","shallnt":"shall not","shant":"shall not","shed":"she had","shell":"she shall","shes":"she is","shouldve":"should have","shouldnt":"should not","shouldntve":"should not have","somebodys":"somebody is","someones":"someone is","somethings":"something is","thatll":"that shall","thatre":"that are","thatd":"that would","thered":"there had","therell":"there shall","therere":"there are","theres":"there is","thesere":"these are","theseve":"these have","theyd":"they had","theyll":"they shall","theyre":"they are","theyve":"they have","thiss":"this is","thosere":"those are","thoseve":"those have","tis":"it is","tove":"to have","twas":"it was","wasnt":"was not","wed":"we had","wedve":"we would have","were":"we are","weve":"we have","werent":"were not","whatd":"what did","whatll":"what shall","whatre":"what are","whats":"what is","whatve":"what have","whens":"when is","whered":"where did","wherell":"where shall","wherere":"where are","wheres":"where is","whereve":"where have","whichd":"which had","whichll":"which shall","whichre":"which are","whichs":"which is","whichve":"which have","whod":"who would","whodve":"who would have","wholl":"who shall","whore":"who are","whos":"who is","whove":"who have","whyd":"why did","whyre":"why are","whys":"why is","wont":"will not","wouldve":"would have","wouldnt":"would not","wouldntve":"would not have","yall":"you all","yalldve":"you all would have","yallre":"you all are","youd":"you had","youll":"you shall","youre":"you are","youve":"you have","'re":"are","thats":"that is"}

requirements.txt

@@ -0,0 +1,7 @@
+streamlit == 1.27.1
+Pillow == 9.4.0
+nltk == 3.8.1
+numpy == 1.24.3
+pandas == 2.0.3
+tensorflow  == 2.14.0
+regex == 2022.7.9

stopwords.csv

@@ -0,0 +1,451 @@
+0
+provided that
+sixty
+although
+don't
+'s
+ve
+which
+can
+anywhere
+name
+down
+versus
+seem
+formerly
+hereupon
+’re
+u
+you're
+do
+them
+has
+didn
+it's
+beside
+so
+z
+third
+whether
+here
+whether or not
+didn't
+hasn
+isn't
+where
+our
+full
+six
+anyhow
+most
+outside
+out
+those
+hadn't
+again
+against
+won
+ours
+having
+both
+all
+together
+me
+been
+latterly
+go
+have
+other
+anything
+if
+please
+did
+aren
+any
+mustn't
+minus
+several
+n’t
+thru
+itself
+anyway
+’ll
+toward
+as much as
+yourself
+alone
+during
+must
+himself
+eight
+j
+hers
+‘d
+'ll
+wasn
+'m
+needn't
+doing
+already
+into
+s
+between
+shouldn
+would
+either
+yet
+mightn
+part
+eleven
+meanwhile
+of
+after
+whatever
+become
+she's
+nowhere
+that
+us
+the
+latter
+ûï
+herself
+like
+this
+becoming
+beforehand
+g
+l
+despite
+whoever
+supposing
+still
+may
+always
+her
+not
+'d
+as long as
+upon
+near
+get
+twelve
+his
+d
+with
+could
+done
+shouldn't
+twenty
+thus
+’ve
+nor
+‘m
+ourselves
+see
+sometimes
+below
+in order that
+than
+least
+that'll
+ûò
+take
+thereafter
+unlike
+behind
+round
+ûªs
+or
+call
+on
+say
+their
+within
+across
+well
+serious
+nevertheless
+neither
+what
+four
+c
+who
+via
+ûªve
+further
+keep
+’s
+over
+about
+for
+till
+when
+often
+its
+someone
+became
+him
+being
+how
+be
+per
+are
+whole
+perhaps
+lest
+noone
+two
+mine
+q
+others
+thence
+doesn't
+amongst
+really
+isn
+wouldn't
+to
+until
+inside
+before
+ten
+yourselves
+he
+such
+my
+shan't
+at
+whereafter
+side
+v
+themselves
+somehow
+‘ve
+nine
+empty
+few
+through
+anyone
+whence
+we
+following
+shan
+amid
+only if
+cannot
+whereupon
+ìñ
+plus
+hadn
+h
+up
+’d
+many
+put
+you'd
+beyond
+much
+enough
+ûówe
+theirs
+around
+besides
+f
+were
+y
+hereafter
+is
+then
+you've
+aren't
+ì
+rather
+made
+almost
+elsewhere
+whose
+fifteen
+should've
+back
+e
+very
+haven
+ca
+once
+x
+also
+else
+show
+whereas
+underneath
+unless
+yours
+‘re
+regarding
+wherein
+you
+otherwise
+she
+k
+less
+aboard
+o
+ã
+whereby
+first
+mustn
+make
+you'll
+sometime
+towards
+due
+give
+in case
+bottom
+ï
+considering
+concerning
+onto
+does
+while
+had
+now that
+since
+same
+without
+therefore
+by
+doesn
+mostly
+as though
+should
+every
+some
+seems
+off
+w
+by the time
+am
+û
+a
+from
+couldn't
+ûó
+thereby
+front
+top
+whither
+as
+indeed
+r
+therein
+used
+now
+i
+will
+even
+ll
+none
+ever
+even if
+becomes
+couldn
+above
+just
+in the event that
+nothing
+ûªm
+whenever
+except
+hereby
+along
+don
+was
+own
+mightn't
+three
+p
+n‘t
+throughout
+even though
+wherever
+afterwards
+and
+n
+they
+there
+last
+never
+b
+’m
+these
+t
+former
+amount
+myself
+nobody
+ûª
+wouldn
+among
+each
+m
+your
+something
+hasn't
+however
+needn
+but
+hence
+five
+wasn't
+seemed
+too
+everyone
+as if
+haven't
+n't
+re
+thereupon
+one
+no
+various
+why
+under
+whom
+somewhere
+in
+namely
+might
+more
+fifty
+another
+everything
+next
+ma
+forty
+won't
+seeming
+as soon as
+‘ll
+everywhere
+an
+quite
+weren
+though
+beneath
+hundred
+it
+‘s
+ain
+using
+weren't
+å
+moreover
+because
+ûªre
+herein
+move
+'ve
+only
+'re

transfer_tweet/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376041931ca2355913e3c847180a34408d8ffa2ebd01ddbd964f4fce7cb476d0
+size 57

transfer_tweet/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dca4e0121922693287b38f14447d072fabd04e089cd6487964e6e5261e32ff9
+size 21175

transfer_tweet/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecab5be566dc4fd13a897026c2e7ab549989858410f1a5fa1a091842a75e77dd
+size 10031550

transfer_tweet/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb76923e9a19466c1ef9aa371b9783c8218f05cdc91340af81ddcae1bae72689
+size 1029458023