Duplicate from curtpond/lr_prototype

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,14 @@
+---
+title: Lr Prototype
+emoji: 🦀
+colorFrom: red
+colorTo: blue
+sdk: gradio
+sdk_version: 3.18.0
+app_file: app.py
+pinned: false
+license: cc
+duplicated_from: curtpond/lr_prototype
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,55 @@
+# Imports
+import gradio as gr
+from sklearn.linear_model import LogisticRegression
+import pickle5 as pickle
+import re
+import string
+import nltk
+from nltk.corpus import stopwords
+nltk.download('stopwords')
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+# Load pickled model and vectorizer
+model = 'lr_021823.pkl'
+model_loaded = pickle.load(open(model, 'rb'))
+vectorizer = 'vectorizer_021823.pkl'
+vectorizer_loaded = pickle.load(open(vectorizer, 'rb'))
+
+
+# Process input text, including removing stopwords, converting to lowercase, and removing punctuation
+stop = stopwords.words('english')
+def process_text(text):
+    text = [word for word in text.split() if word not in stop]
+    text = str(text).lower()
+    text = re.sub(
+        f"[{re.escape(string.punctuation)}]", " ", text
+    )
+    text = " ".join(text.split())
+    return text
+
+# Vectorize text
+def vectorize_text(text):
+    text = process_text(text)
+    text = vectorizer_loaded.transform([text])
+    return text
+
+# Valid input for the model so number of features match
+def class_predict(text):
+    text = process_text(text)
+    vec = vectorizer_loaded.transform([text])
+    prediction = model_loaded.predict(vec)
+    return prediction
+
+
+# Define interface
+demo = gr.Interface(fn=class_predict,
+                        title="Text Classification Demo",
+                        description="This is a demo of a text classification model using Logistic Regression.",
+                        inputs=gr.Textbox(lines=10, placeholder='Input text here...', label="Input Text"),
+                        outputs=gr.Textbox(label="Predicted Label: Healthcare: 0, Other: 1, Technology: 2", lines=2, placeholder='Predicted label will appear here...'),
+                        allow_flagging='never'
+)
+
+demo.launch()
+

lr_021223.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7036cd9deddab77f465e6ab534fdd70552345530e10360e2ffc971c2d628e81
+size 132

lr_021823.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:633ffaf2cdcd72308a63c45058e640e5fde3a97aa07559a112fa616992ec62ef
+size 3886406

requirements.txt

@@ -0,0 +1,4 @@
+scikit-learn==1.1.1
+pickle5
+flair
+nltk==3.8.1

vectorizer_021223.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c0a94be456efa18f6357794cea11ec493939426b35073aa737de9d31edde7a
+size 132

vectorizer_021823.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539dadc0945808b81723497ab0a9a5c9ddf2bc0ddf724a946f41e3cbc4846662
+size 2375371