Upload 6 files

bank_statement.csv

@@ -0,0 +1,12 @@
+Date,Description,Amount (USD)
+2024-01-01,Walmart,35.20
+2024-01-02,Shell Gas Station,45.00
+2024-01-03,Netflix,15.99
+2024-01-04,Starbucks,4.50
+2024-01-05,Verizon Wireless,60.00
+2024-01-06,Target,85.00
+2024-01-07,Whole Foods,70.30
+2024-01-08,AMC Theatres,25.00
+2024-01-09,Spotify,9.99
+2024-01-10,Chick-fil-A,18.40
+2024-01-11,ExxonMobil,50.00

pages/1_a.py

@@ -0,0 +1,66 @@
+import os
+from langchain.llms.openai import OpenAI
+from langchain.llms.bedrock import Bedrock
+from langchain_google_genai import GoogleGenerativeAI
+from langchain.prompts import PromptTemplate
+from langchain.chains import SimpleSequentialChain
+from langchain.chains import LLMChain
+# Pixegami
+
+PROMPT_TEMPLATE_TEXT = """
+Generate a table in CSV format from the following bank statement data.
+
+Add a column called "Category" and populate it with one of the following values: 
+[Groceries, Transport, Entertainment, Shopping, Utilities, Eating Out, Unknown]
+
+{statement}
+"""
+
+CODING_TEMPLATE_TEXT = """
+First, hard-code this data as a Python variable called 'items', with the category name and value.
+Then write a Python script to sum this data by 'Category' and print the results.
+
+{categorized_transactions}
+"""
+
+
+# OpenAI (GPT-3.5) LLM
+llm_open_ai = OpenAI(max_tokens=1024)
+
+# AWS Bedrock LLM
+BEDROCK_CLAUDE_MODEL = "anthropic.claude-v2"
+BEDROCK_LLAMA_MODEL = "meta.llama2-70b-chat-v1"
+llm_bedrock = Bedrock(
+    credentials_profile_name="default",
+    model_id=BEDROCK_CLAUDE_MODEL,
+    model_kwargs={"max_tokens_to_sample": 1024},
+)
+
+# Google Gemini LLM
+llm_gemini = GoogleGenerativeAI(
+    model="gemini-pro",
+    max_output_tokens=1024,
+    google_api_key=os.environ["GOOGLE_AI_API_KEY"],
+)
+
+llm = llm_gemini  # Or llm_bedrock or llm_open_ai.
+
+# Create the individual prompt templates.
+categorization_template = PromptTemplate.from_template(PROMPT_TEMPLATE_TEXT)
+coding_template = PromptTemplate.from_template(CODING_TEMPLATE_TEXT)
+
+# Create the chains.
+categorization_chain = LLMChain(llm=llm, prompt=categorization_template)
+coding_chain = LLMChain(llm=llm, prompt=coding_template)
+
+# Join them into a sequential chain.
+overall_chain = SimpleSequentialChain(
+    chains=[categorization_chain, coding_chain], verbose=True
+)
+
+# Load the bank statement data.
+with open("bank_statement.csv", "r") as f:
+    bank_statement_data = f.read()
+
+# Run the chain using the bank statement data as input.
+overall_chain.run(bank_statement_data)

pages/2_hotdog.py

@@ -0,0 +1,19 @@
+import streamlit as st
+from transformers import pipeline
+from PIL import Image
+
+
+st.header(':red[2]',divider='violet')
+
+st.subheader('Hotdog or Not Hotdog?')
+pipeline = pipeline(task='image-classification', model='julien-c/hotdog-not-hotdog')
+file_name = st.file_uploader("Upload a hotdog candidate image")
+
+if file_name is not None:
+    col1, col2 = st.columns(2)
+    image = Image.open(file_name)
+    col1.image(image, use_column_width=True)
+    predictions = pipeline(image)
+    col2.header("Probabilities")
+    for p in predictions:
+        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")

pages/3_hf_tutorial.py

@@ -0,0 +1,84 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from transformers import pipeline
+import time
+import html
+
+st.title('3 - *HuggingFace* :blue[Tutorial]')
+
+def slowly_display_text(text, delay=0.05):
+    # Define the CSS for the text container
+    css = """
+    <style>
+    .text-container {
+        width: 80%;
+        max-width: 600px;
+        white-space: pre-wrap; /* Ensure text wraps */
+        word-wrap: break-word; /* Ensure long words wrap */
+        font-family: 'Courier New', Courier, monospace;
+        font-size: 1.1em;
+        line-height: 1.5;
+    }
+    </style>
+    """
+    
+    # Create a placeholder for the text
+    placeholder = st.empty()
+    displayed_text = ""
+    
+    # Iterate over each character and update the text incrementally
+    for char in text:
+        displayed_text += html.escape(char)  # Escape HTML special characters
+        # Replace newlines with <br> tags to handle empty lines correctly
+        formatted_text = displayed_text.replace("\n", "<br>")
+        placeholder.markdown(css + f'<div class="text-container">{formatted_text}</div>', unsafe_allow_html=True)
+        time.sleep(delay)
+
+######################################################
+st.subheader('Pipe1 :- Sentiment Analysis',divider='orange')
+
+if st.checkbox(label='Show Pipe1'):
+    classifier = pipeline('sentiment-analysis')
+
+    x = st.text_input(label='Enter text', value="I've been waiting for a huggingface course my whoole life.")
+    res = classifier(x)
+    # st.markdown(body=f"*Prediction*: :green-background[{res[0]['label']}]")
+    # st.markdown(f"*Score*: :green-background[{res[0]['score']}]")
+    col1, col2 = st.columns(2)
+    col1.metric(label='Prediction', value=res[0]['label'])
+    col2.metric(label='Score', value=res[0]['score'])
+    st.write(res)
+
+######################################################
+st.subheader('Pipe2 :- Text Generation',divider='orange')
+
+if st.checkbox(label='Show Pipe2'):
+    generator = pipeline('text-generation', model='distilgpt2')
+    sentence = "In this course we'll teach you how to"
+    res2 = generator(
+        sentence,
+        max_length = 30,
+    )
+    x = st.text_input(label='Enter text', value="In this course we'll teach you how to")
+    res2 = generator(x,max_length=70)
+    st.write("Generated text is:")
+    slowly_display_text(res2[0]['generated_text'])
+    st.write(res2)
+
+
+######################################################
+st.subheader('Pipe3 :- Zero-shot classification', divider='orange')
+
+if st.checkbox(label='Show Pipe3'):
+    clf2 = pipeline(
+        task='zero-shot-classification',
+        model = 'distilbert/distilbert-base-uncased-finetuned-sst-2-english',
+        framework='pt'
+    )
+    x = st.text_input(label='Enter text', value="This is a course about python list comprehension")
+    res3 = clf2(
+        x,
+        candidate_labels = ['education', 'politics', 'business']
+    )
+    st.write(res3)

pages/4_all.py

@@ -0,0 +1,36 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import time
+
+st.header(body=':red[4]', divider='violet')
+st.sidebar.markdown('Page 4 :snowflake:')
+if st.checkbox(label='Show DataFrame'):
+    chart_data = pd.DataFrame(
+        np.random.randn(20,3),
+        columns=['a','b','c']
+    )
+    chart_data
+
+if st.checkbox(label='Show time progess bar'):
+    'Starting a long computation'
+
+    # add a placeholder
+    latest_iteration = st.empty()
+    bar = st.progress(0)
+
+    for i in range(100):
+        # Update the progress bar with each iteration
+        latest_iteration.text(f"Iteration {i+1}")
+        bar.progress(i + 1)
+        time.sleep(0.2)
+
+    '.. and now we\'re done!'
+
+if "counter" not in st.session_state:
+    st.session_state.counter = 0
+
+st.session_state.counter += 1
+
+st.write(f"This page has run {st.session_state.counter} times.")
+st.button("Run it again")

pages/5_Uber_from_doc.py

@@ -0,0 +1,36 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+
+st.title('Uber pickups in NYC')
+
+DATE_COLUMN = 'date/time'
+DATA_URL = ('https://s3-us-west-2.amazonaws.com/'
+            'streamlit-demo-data/uber-raw-data-sep14.csv.gz')
+
+@st.cache_data
+def load_data(nrows):
+    data = pd.read_csv(DATA_URL, nrows=nrows)
+    lowercase = lambda x: str(x).lower()
+    data.rename(lowercase, axis='columns', inplace=True)
+    data[DATE_COLUMN] = pd.to_datetime(data[DATE_COLUMN])
+    return data
+
+data_load_state = st.text('Loading data...')
+data = load_data(10000)
+data_load_state.text("Done! (using st.cache_data)")
+
+if st.checkbox('Show raw data'):
+    st.subheader('Raw data')
+    st.write(data)
+
+st.subheader('Number of pickups by hour')
+hist_values = np.histogram(data[DATE_COLUMN].dt.hour, bins=24, range=(0,24))[0]
+st.bar_chart(hist_values)
+
+# Some number in the range 0-23
+hour_to_filter = st.slider('hour', 0, 23, 17)
+filtered_data = data[data[DATE_COLUMN].dt.hour == hour_to_filter]
+
+st.subheader('Map of all pickups at %s:00' % hour_to_filter)
+st.map(filtered_data)