Software & Tools AI

Jupyter Lab Interactive Python for EDA and experimentation. ``bash pip install jupyterlab jupyter lab jupyter nbconvert nb.ipynb --to script ``

VS Code Extensions for AI
• Python: IntelliSense, debugging, refactoring
• Jupyter: run notebooks in VS Code
• GitHub Copilot: AI pair programmer
• Remote SSH: code on cloud GPUs locally

Virtual Environments ```bash python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt

# Modern: uv (fast Rust-based) pip install uv uv venv && uv pip install pandas torch transformers ```

from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
from datasets import load_dataset

# Pipeline API highest level classifier = pipeline("sentiment-analysis") result = classifier("This movie was amazing!")

generator = pipeline("text-generation", model="gpt2") result = generator("The future of AI is", max_new_tokens=50)

# Load any model tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased") model = AutoModelForSequenceClassification.from_pretrained( "distilbert-base-uncased-finetuned-sst-2-english" )

# Datasets dataset = load_dataset("imdb") train_ds = dataset["train"].shuffle(seed=42).select(range(1000))

# Push to Hub model.push_to_hub("my-username/my-model") tokenizer.push_to_hub("my-username/my-model") ```

from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain.prompts import ChatPromptTemplate
from langchain.schema.output_parser import StrOutputParser
from langchain_community.vectorstores import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter

# Basic chain llm = ChatOpenAI(model="gpt-4o-mini", temperature=0) prompt = ChatPromptTemplate.from_messages([ ("system", "You are a helpful assistant. Answer in {language}."), ("human", "{question}") ]) chain = prompt | llm | StrOutputParser() result = chain.invoke({"question": "What is RAG?", "language": "English"})

# RAG setup from langchain_community.document_loaders import DirectoryLoader docs = DirectoryLoader("./docs", glob="**/*.md").load() chunks = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200).split_documents(docs) vectorstore = Chroma.from_documents(chunks, OpenAIEmbeddings(), persist_directory="./chroma_db") retriever = vectorstore.as_retriever(search_kwargs={"k": 4}) ```

import mlflow
import mlflow.sklearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, f1_score

mlflow.set_tracking_uri("http://localhost:5000") mlflow.set_experiment("customer-churn-prediction")

with mlflow.start_run(run_name="rf-baseline"): params = {"n_estimators": 100, "max_depth": 10, "random_state": 42} mlflow.log_params(params)

model = RandomForestClassifier(**params) model.fit(X_train, y_train) y_pred = model.predict(X_test)

mlflow.log_metrics({ "accuracy": accuracy_score(y_test, y_pred), "f1": f1_score(y_test, y_pred, average="weighted"), }) mlflow.sklearn.log_model(model, "model", registered_model_name="churn-predictor")

# Load for inference model = mlflow.sklearn.load_model("models:/churn-predictor/Production") ```

from openai import OpenAI
from pydantic import BaseModel
from typing import List

client = OpenAI()

# Basic completion response = client.chat.completions.create( model="gpt-4o-mini", messages=[ {"role": "system", "content": "You are an expert data analyst."}, {"role": "user", "content": "Revenue dropped 30% in Q3. Analyze."} ], temperature=0.3 ) print(response.choices[0].message.content)

# Structured output (Pydantic schema) class DataInsight(BaseModel): summary: str root_causes: List[str] recommendations: List[str] severity: str # "low", "medium", "high"

response = client.beta.chat.completions.parse( model="gpt-4o", messages=[{"role": "user", "content": "Revenue dropped 30% Q3 vs Q2."}], response_format=DataInsight ) insight = response.choices[0].message.parsed print(insight.severity, insight.recommendations)

# Embeddings response = client.embeddings.create( model="text-embedding-3-small", input=["Machine learning is powerful"] ) embedding = response.data[0].embedding # 1536-dim vector ```