Add application file

app.py

@@ -0,0 +1,49 @@
+import streamlit as st
+import pickle
+
+
+import numpy as np
+import pandas as pd
+import re
+import string
+import nltk      
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import confusion_matrix, classification_report 
+import matplotlib.pyplot as plt
+from sklearn.metrics import plot_confusion_matrix
+
+
+stopwords = nltk.corpus.stopwords.words('english')
+
+def text_clean(text):
+    clean_words = []
+    
+    word_L = text.split()
+    for w in word_L:
+        word_l = w.lower().strip()
+        if word_l.isalpha():
+            if len(word_l) > 3:
+                if word_l not in stopwords :
+                    clean_words.append(word_l)
+                else:
+                    continue
+    return clean_words  
+
+model = pickle.load(open("model.pickle", "rb"))
+tfidf = pickle.load(open("tfidf.pickle","rb"))
+
+
+st.header("NLP Consumer Complaints")
+
+st.write("Please enter the complaint")
+
+t = st.text_area("comp")
+
+print(model.predict(tfidf.transform([t]).toarray()))
+
+b = st.button("Submit")
+
+if len(t) > 0 and b:
+    st.write(model.predict(tfidf.transform([t]).toarray())[0])

model.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aed7645b2cdff9247d0227e6e75b5943bbf8393cd15e046d968d6ffd26d6e18
+size 1731983

requirements.txt

@@ -0,0 +1 @@
+fastai

tfidf.pickle

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7c5cea3f05237f9156993e672aa8ece2d1fc4766eba4a0f80593843cf8511e
+size 1610937