Initialize Project

Dockerfile

@@ -10,6 +10,7 @@ RUN apt-get update && apt-get install -y \
 
 COPY requirements.txt ./
 COPY src/ ./src/
+COPY saved_models/ ./saved_models/
 
 RUN pip3 install -r requirements.txt
 

requirements.txt

@@ -1,3 +1,17 @@
-altair
+transformers
+datasets
+torch
+scikit-learn
+jupyterlab
+matplotlib
+seaborn
+sentencepiece
+python-dotenv
+evaluate
 pandas
-streamlit
+tqdm
+streamlit
+selenium==4.31.0 
+webdriver-manager==4.0.2
+numpy
+joblib

saved_models/distilbert_distilbert-base-uncased-finetuned-banking77/config.json

@@ -0,0 +1,182 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47",
+    "48": "LABEL_48",
+    "49": "LABEL_49",
+    "50": "LABEL_50",
+    "51": "LABEL_51",
+    "52": "LABEL_52",
+    "53": "LABEL_53",
+    "54": "LABEL_54",
+    "55": "LABEL_55",
+    "56": "LABEL_56",
+    "57": "LABEL_57",
+    "58": "LABEL_58",
+    "59": "LABEL_59",
+    "60": "LABEL_60",
+    "61": "LABEL_61",
+    "62": "LABEL_62",
+    "63": "LABEL_63",
+    "64": "LABEL_64",
+    "65": "LABEL_65",
+    "66": "LABEL_66",
+    "67": "LABEL_67",
+    "68": "LABEL_68",
+    "69": "LABEL_69",
+    "70": "LABEL_70",
+    "71": "LABEL_71",
+    "72": "LABEL_72",
+    "73": "LABEL_73",
+    "74": "LABEL_74",
+    "75": "LABEL_75",
+    "76": "LABEL_76"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "LABEL_48": 48,
+    "LABEL_49": 49,
+    "LABEL_5": 5,
+    "LABEL_50": 50,
+    "LABEL_51": 51,
+    "LABEL_52": 52,
+    "LABEL_53": 53,
+    "LABEL_54": 54,
+    "LABEL_55": 55,
+    "LABEL_56": 56,
+    "LABEL_57": 57,
+    "LABEL_58": 58,
+    "LABEL_59": 59,
+    "LABEL_6": 6,
+    "LABEL_60": 60,
+    "LABEL_61": 61,
+    "LABEL_62": 62,
+    "LABEL_63": 63,
+    "LABEL_64": 64,
+    "LABEL_65": 65,
+    "LABEL_66": 66,
+    "LABEL_67": 67,
+    "LABEL_68": 68,
+    "LABEL_69": 69,
+    "LABEL_7": 7,
+    "LABEL_70": 70,
+    "LABEL_71": 71,
+    "LABEL_72": 72,
+    "LABEL_73": 73,
+    "LABEL_74": 74,
+    "LABEL_75": 75,
+    "LABEL_76": 76,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.57.1",
+  "vocab_size": 30522
+}

saved_models/distilbert_distilbert-base-uncased-finetuned-banking77/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb9a1354f898d570a195359d2050bd80e97c505caef07372891ef72118af3d6
+size 268063276

saved_models/distilbert_distilbert-base-uncased-finetuned-banking77/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

saved_models/distilbert_distilbert-base-uncased-finetuned-banking77/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

saved_models/distilbert_distilbert-base-uncased-finetuned-banking77/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9251dd2260f588c4fa12d97412fa8019070e4a667daacda44f1836364a87079
+size 5905

src/streamlit_app.py

@@ -1,40 +1,95 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+from transformers import pipeline
+from datasets import load_dataset
+import torch
+import os
+
+def load_css(file_name):
+    current_dir = os.path.dirname(__file__)
+    css_file_path = os.path.join(current_dir, file_name)
+    with open(css_file_path) as f:
+        st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)
+
+load_css("style.css")
+
+st.set_page_config(
+    page_title="Intent Classification in Banking",
+    page_icon="🤖",
+    layout="centered"
+)
+
+@st.cache_resource
+def load_model_and_mapping():
+    model_path = "saved_models/distilbert_distilbert-base-uncased-finetuned-banking77"
+    
+    device = 0 if torch.cuda.is_available() else -1
+    classifier = pipeline("text-classification", model=model_path, device=device)
+    
+    raw_datasets = load_dataset("mteb/banking77")
+    df_train = raw_datasets['train'].to_pandas()
+    
+    label_mapping_df = df_train[['label', 'label_text']].drop_duplicates().reset_index(drop=True)
+    
+    return classifier, label_mapping_df
+
+classifier, label_mapping_df = load_model_and_mapping()
+
+st.title("Intent Classification in Banking")
+
+st.markdown(
+    """
+    This is a demo for a language model that has been fine-tuned to classify 77 different types of customer requests in the banking sector.
+    """
+)
+
+with st.form("intent_form"):
+    user_input = st.text_area("Please enter your request here:", "", height=100)
+    submitted = st.form_submit_button("Classify Intent")
+
+if submitted and user_input:
+    with st.spinner('The model is analyzing...'):
+        predictions = classifier(user_input, top_k=5)
+        
+        mapped_predictions = []
+        for pred in predictions:
+            label_id = int(pred['label'].split('_')[1])
+            
+            matched_row = label_mapping_df[label_mapping_df['label'] == label_id]
+            
+            if not matched_row.empty:
+                label_text = matched_row['label_text'].iloc[0]
+            else:
+                label_text = "Cannot find label"
+            
+            mapped_predictions.append({'label': label_text, 'score': pred['score']})
+
+        top_prediction = mapped_predictions[0]
+        
+        st.success(f"**The top predicted intent is:** `{top_prediction['label']}`")
+        st.metric(label="With confidence", value=f"{top_prediction['score']:.2%}")
+        
+        st.markdown("---")
+        
+        st.subheader("Other possibilities:")
+        
+        df = pd.DataFrame(mapped_predictions)
+        df = df.rename(columns={'label': 'Intent', 'score': 'Confidence'})
+        df['Confidence'] = df['Confidence'].apply(lambda x: f"{x:.2%}")
+
+        st.dataframe(
+            df,
+            column_config={
+                "Confidence": st.column_config.ProgressColumn(
+                    "Confidence",
+                    format="%.3f",
+                    min_value=0,
+                    max_value=1,
+                ),
+            },
+            hide_index=True,
+            width='stretch'
+        )
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+elif submitted and not user_input:
+    st.warning("Please enter a request to classify.")

src/style.css

@@ -0,0 +1,6 @@
+.stApp {
+    background-image: url("https://img.freepik.com/free-photo/abstract-luxury-gradient-blue-background-smooth-dark-blue-with-black-vignette-studio-banner_1258-63468.jpg");
+    background-size: cover;
+    background-repeat: no-repeat;
+    background-attachment: fixed;
+}