diff --git a/.gitconfig b/.gitconfig
new file mode 100644
index 000000000..e69de29bb
diff --git a/docker-compose.yml b/docker-compose.yml
index 9decd7127..ed4caff8a 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -38,6 +38,16 @@ services:
     restart: always
     networks:
       - app-network
+  mlflow:
+    build:
+      context: .
+      dockerfile: mlflow.dockerfile
+    ports:
+      - "5000:5000"
+    volumes:
+      - "${PWD}/mlflow:/home/mlflow/"
+    networks:
+      - app-network
 networks:
   app-network:
     driver: bridge
diff --git a/finalized_model.lib b/finalized_model.lib
new file mode 100644
index 000000000..1173672fc
Binary files /dev/null and b/finalized_model.lib differ
diff --git a/mlflow.dockerfile b/mlflow.dockerfile
new file mode 100644
index 000000000..627691e95
--- /dev/null
+++ b/mlflow.dockerfile
@@ -0,0 +1,12 @@
+FROM python:3.10-slim
+
+RUN pip install mlflow==2.12.1
+
+EXPOSE 5000
+
+CMD [ \
+    "mlflow", "server", \
+    "--backend-store-uri", "sqlite:///home/mlflow/mlflow.db", \
+    "--host", "0.0.0.0", \
+    "--port", "5000" \
+]
\ No newline at end of file
diff --git a/mlflow_artifacts/dv_artifact.pkl b/mlflow_artifacts/dv_artifact.pkl
new file mode 100644
index 000000000..2dacf43da
Binary files /dev/null and b/mlflow_artifacts/dv_artifact.pkl differ
diff --git a/mlops/homework_03/.gitignore b/mlops/homework_03/.gitignore
new file mode 100755
index 000000000..8b3e82f61
--- /dev/null
+++ b/mlops/homework_03/.gitignore
@@ -0,0 +1,14 @@
+.DS_Store
+.file_versions
+.gitkeep
+.log
+.logs/
+.mage_temp_profiles
+.preferences.yaml
+.variables/
+__pycache__/
+docker-compose.override.yml
+logs/
+mage-ai.db
+mage_data/
+secrets/
diff --git a/mlops/homework_03/__init__.py b/mlops/homework_03/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/charts/__init__.py b/mlops/homework_03/charts/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/custom/__init__.py b/mlops/homework_03/custom/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/data_exporters/__init__.py b/mlops/homework_03/data_exporters/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/data_exporters/build.py b/mlops/homework_03/data_exporters/build.py
new file mode 100644
index 000000000..c5537bf7d
--- /dev/null
+++ b/mlops/homework_03/data_exporters/build.py
@@ -0,0 +1,67 @@
+import os
+import mlflow
+import mlflow.sklearn
+from sklearn.feature_extraction import DictVectorizer
+from sklearn.linear_model import LinearRegression 
+import joblib
+
+# Set experiment id
+mlflow.set_experiment('mage_lr_experiment')
+
+# Set tracking uri
+# mlflow.set_tracking_uri('http://localhost:5000')
+
+if 'data_exporter' not in globals():
+    from mage_ai.data_preparation.decorators import data_exporter
+
+
+@data_exporter
+def export_data(data, *args, **kwargs):
+    """
+    Exports data to some source.
+
+    Args:
+        data: The output from the upstream parent block
+        args: The output from any additional upstream blocks (if applicable)
+
+    Output (optional):
+        Optionally return any object and it'll be logged and
+        displayed when inspecting the block run.
+    """
+    # Specify your transformation logic here
+    df_train = data
+
+    # turn dictionary into vector
+    dv = DictVectorizer()
+    train_dicts = df_train[['PULocationID', 'DOLocationID']].to_dict(orient='records')
+
+    # Feature matrix
+    X_train = dv.fit_transform(train_dicts)
+
+    # Target matrix
+    target = 'duration'
+    y_train = df_train[target].values   
+
+    # Build model
+    model = LinearRegression()
+    model.fit(X_train, y_train)
+
+    # Specify artifact_path
+    artifact_directory = 'mlflow_artifacts'
+
+    # Create directory if it doesnt exist
+    os.makedirs(artifact_directory, exist_ok=True)
+
+    # Save and log the artifact (DictVectorizer)
+    artifact_path =  os.path.join(artifact_directory, "dv_artifact.pkl")
+
+    with open(artifact_path, 'wb') as f:
+        joblib.dump(dv, f)
+
+    # Log the linear regression model with MLflow
+    with mlflow.start_run():
+        mlflow.sklearn.log_model(model, "linear_regression_model")
+        mlflow.log_param("intercept", model.intercept_)
+        mlflow.log_artifact(artifact_path)
+    
+    return model, dv
\ No newline at end of file
diff --git a/mlops/homework_03/data_exporters/export_titanic_clean.py b/mlops/homework_03/data_exporters/export_titanic_clean.py
new file mode 100755
index 000000000..cb7aa63aa
--- /dev/null
+++ b/mlops/homework_03/data_exporters/export_titanic_clean.py
@@ -0,0 +1,16 @@
+from mage_ai.io.file import FileIO
+from pandas import DataFrame
+
+if 'data_exporter' not in globals():
+    from mage_ai.data_preparation.decorators import data_exporter
+
+
+@data_exporter
+def export_data_to_file(df: DataFrame, **kwargs) -> None:
+    """
+    Template for exporting data to filesystem.
+
+    Docs: https://docs.mage.ai/design/data-loading#example-loading-data-from-a-file
+    """
+    filepath = 'titanic_clean.csv'
+    FileIO().export(df, filepath)
diff --git a/mlops/homework_03/data_loaders/__init__.py b/mlops/homework_03/data_loaders/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/data_loaders/ingest.py b/mlops/homework_03/data_loaders/ingest.py
new file mode 100644
index 000000000..5787b568a
--- /dev/null
+++ b/mlops/homework_03/data_loaders/ingest.py
@@ -0,0 +1,28 @@
+import requests
+from io import BytesIO
+from typing import List
+
+import pandas as pd
+
+
+if 'data_loader' not in globals():
+    from mage_ai.data_preparation.decorators import data_loader
+
+
+@data_loader
+def load_data(*args, **kwargs):
+    """
+    Template code for loading data from any source.
+
+    Returns:
+        Anything (e.g. data frame, dictionary, array, int, str, etc.)
+    """
+    # Specify your data loading logic here
+    response = requests.get("https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2023-03.parquet")
+
+    if response.status_code != 200:
+        raise Exception(response.text)
+
+    df = pd.read_parquet(BytesIO(response.content))
+    
+    return df
\ No newline at end of file
diff --git a/mlops/homework_03/data_loaders/load_titanic.py b/mlops/homework_03/data_loaders/load_titanic.py
new file mode 100755
index 000000000..c664e0f2d
--- /dev/null
+++ b/mlops/homework_03/data_loaders/load_titanic.py
@@ -0,0 +1,27 @@
+import io
+import pandas as pd
+import requests
+from pandas import DataFrame
+
+if 'data_loader' not in globals():
+    from mage_ai.data_preparation.decorators import data_loader
+if 'test' not in globals():
+    from mage_ai.data_preparation.decorators import test
+
+
+@data_loader
+def load_data_from_api(**kwargs) -> DataFrame:
+    """
+    Template for loading data from API
+    """
+    url = 'https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv?raw=True'
+
+    return pd.read_csv(url)
+
+
+@test
+def test_output(df) -> None:
+    """
+    Template code for testing the output of the block.
+    """
+    assert df is not None, 'The output is undefined'
diff --git a/mlops/homework_03/dbt/profiles.yml b/mlops/homework_03/dbt/profiles.yml
new file mode 100755
index 000000000..90599f894
--- /dev/null
+++ b/mlops/homework_03/dbt/profiles.yml
@@ -0,0 +1,9 @@
+# https://docs.getdbt.com/docs/core/connect-data-platform/profiles.yml
+
+base:
+  outputs:
+
+    dev:
+      type: duckdb
+
+  target: dev
diff --git a/mlops/homework_03/extensions/__init__.py b/mlops/homework_03/extensions/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/interactions/__init__.py b/mlops/homework_03/interactions/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/io_config.yaml b/mlops/homework_03/io_config.yaml
new file mode 100755
index 000000000..80b4d9cef
--- /dev/null
+++ b/mlops/homework_03/io_config.yaml
@@ -0,0 +1,134 @@
+version: 0.1.1
+default:
+  # Default profile created for data IO access.
+  # Add your credentials for the source you use, and delete the rest.
+  # AWS
+  AWS_ACCESS_KEY_ID: "{{ env_var('AWS_ACCESS_KEY_ID') }}"
+  AWS_SECRET_ACCESS_KEY: "{{ env_var('AWS_SECRET_ACCESS_KEY') }}"
+  AWS_SESSION_TOKEN: session_token (Used to generate Redshift credentials)
+  AWS_REGION: region
+  # Algolia
+  ALGOLIA_APP_ID: app_id
+  ALGOLIA_API_KEY: api_key
+  ALGOLIA_INDEX_NAME: index_name
+  # Azure
+  AZURE_CLIENT_ID: "{{ env_var('AZURE_CLIENT_ID') }}"
+  AZURE_CLIENT_SECRET: "{{ env_var('AZURE_CLIENT_SECRET') }}"
+  AZURE_STORAGE_ACCOUNT_NAME: "{{ env_var('AZURE_STORAGE_ACCOUNT_NAME') }}"
+  AZURE_TENANT_ID: "{{ env_var('AZURE_TENANT_ID') }}"
+  # Chroma
+  CHROMA_COLLECTION: collection_name
+  CHROMA_PATH: path
+  # Clickhouse
+  CLICKHOUSE_DATABASE: default
+  CLICKHOUSE_HOST: host.docker.internal
+  CLICKHOUSE_INTERFACE: http
+  CLICKHOUSE_PASSWORD: null
+  CLICKHOUSE_PORT: 8123
+  CLICKHOUSE_USERNAME: null
+  # Druid
+  DRUID_HOST: hostname
+  DRUID_PASSWORD: password
+  DRUID_PATH: /druid/v2/sql/
+  DRUID_PORT: 8082
+  DRUID_SCHEME: http
+  DRUID_USER: user
+  # DuckDB
+  DUCKDB_DATABASE: database
+  DUCKDB_SCHEMA: main
+  # Google
+  GOOGLE_SERVICE_ACC_KEY:
+    type: service_account
+    project_id: project-id
+    private_key_id: key-id
+    private_key: "-----BEGIN PRIVATE KEY-----\nyour_private_key\n-----END_PRIVATE_KEY"
+    client_email: your_service_account_email
+    auth_uri: "https://accounts.google.com/o/oauth2/auth"
+    token_uri: "https://accounts.google.com/o/oauth2/token"
+    auth_provider_x509_cert_url: "https://www.googleapis.com/oauth2/v1/certs"
+    client_x509_cert_url: "https://www.googleapis.com/robot/v1/metadata/x509/your_service_account_email"
+  GOOGLE_SERVICE_ACC_KEY_FILEPATH: "/path/to/your/service/account/key.json"
+  GOOGLE_LOCATION: US # Optional
+  # MongoDB
+  # Specify either the connection string or the (host, password, user, port) to connect to MongoDB.
+  MONGODB_CONNECTION_STRING: "mongodb://{username}:{password}@{host}:{port}/"
+  MONGODB_HOST: host
+  MONGODB_PORT: 27017
+  MONGODB_USER: user
+  MONGODB_PASSWORD: password
+  MONGODB_DATABASE: database
+  MONGODB_COLLECTION: collection
+  # MSSQL
+  MSSQL_DATABASE: database
+  MSSQL_SCHEMA: schema
+  MSSQL_DRIVER: "ODBC Driver 18 for SQL Server"
+  MSSQL_HOST: host
+  MSSQL_PASSWORD: password
+  MSSQL_PORT: 1433
+  MSSQL_USER: SA
+  # MySQL
+  MYSQL_DATABASE: database
+  MYSQL_HOST: host
+  MYSQL_PASSWORD: password
+  MYSQL_PORT: 3306
+  MYSQL_USER: root
+  # Pinot
+  PINOT_HOST: hostname
+  PINOT_PASSWORD: password
+  PINOT_PATH: /query/sql
+  PINOT_PORT: 8000
+  PINOT_SCHEME: http
+  PINOT_USER: user
+  # PostgresSQL
+  POSTGRES_CONNECT_TIMEOUT: 10
+  POSTGRES_DBNAME: postgres
+  POSTGRES_SCHEMA: public # Optional
+  POSTGRES_USER: username
+  POSTGRES_PASSWORD: password
+  POSTGRES_HOST: hostname
+  POSTGRES_PORT: 5432
+  # Qdrant
+  QDRANT_COLLECTION: collection
+  QDRANT_PATH: path
+  # Redshift
+  REDSHIFT_SCHEMA: public # Optional
+  REDSHIFT_DBNAME: redshift_db_name
+  REDSHIFT_HOST: redshift_cluster_id.identifier.region.redshift.amazonaws.com
+  REDSHIFT_PORT: 5439
+  REDSHIFT_TEMP_CRED_USER: temp_username
+  REDSHIFT_TEMP_CRED_PASSWORD: temp_password
+  REDSHIFT_DBUSER: redshift_db_user
+  REDSHIFT_CLUSTER_ID: redshift_cluster_id
+  REDSHIFT_IAM_PROFILE: default
+  # Snowflake
+  SNOWFLAKE_USER: username
+  SNOWFLAKE_PASSWORD: password
+  SNOWFLAKE_ACCOUNT: account_id.region
+  SNOWFLAKE_DEFAULT_WH: null                  # Optional default warehouse
+  SNOWFLAKE_DEFAULT_DB: null                  # Optional default database
+  SNOWFLAKE_DEFAULT_SCHEMA: null              # Optional default schema
+  SNOWFLAKE_PRIVATE_KEY_PASSPHRASE: null      # Optional private key passphrase
+  SNOWFLAKE_PRIVATE_KEY_PATH: null            # Optional private key path
+  SNOWFLAKE_ROLE: null                        # Optional role name
+  SNOWFLAKE_TIMEOUT: null                     # Optional timeout in seconds
+  # Trino
+  trino:
+    catalog: postgresql                       # Change this to the catalog of your choice
+    host: 127.0.0.1
+    http_headers:
+      X-Something: 'mage=power'
+    http_scheme: http
+    password: mage1337                        # Optional
+    port: 8080
+    schema: core_data
+    session_properties:                       # Optional
+      acc01.optimize_locality_enabled: false
+      optimize_hash_generation: true
+    source: trino-cli                         # Optional
+    user: admin
+    verify: /path/to/your/ca.crt              # Optional
+  # Weaviate
+  WEAVIATE_ENDPOINT: https://some-endpoint.weaviate.network
+  WEAVIATE_INSTANCE_API_KEY: YOUR-WEAVIATE-API-KEY
+  WEAVIATE_INFERENCE_API_KEY: YOUR-OPENAI-API-KEY
+  WEAVIATE_COLLECTION: collectionn_name
diff --git a/mlops/homework_03/metadata.yaml b/mlops/homework_03/metadata.yaml
new file mode 100755
index 000000000..bf30d6f5d
--- /dev/null
+++ b/mlops/homework_03/metadata.yaml
@@ -0,0 +1,55 @@
+project_type: standalone
+
+variables_dir: ~/.mage_data
+# remote_variables_dir: s3://bucket/path_prefix
+
+variables_retention_period: '90d'
+
+emr_config:
+  # You can customize the EMR cluster instance size with the two parameters
+  master_instance_type: 'r5.4xlarge'
+  slave_instance_type: 'r5.4xlarge'
+
+  # Configure security groups for EMR cluster instances.
+  # The default managed security groups are ElasticMapReduce-master and ElasticMapReduce-slave
+  # master_security_group: 'sg-xxxxxxxxxxxx'
+  # slave_security_group: 'sg-yyyyyyyyyyyy'
+
+  # If you want to ssh tunnel into EMR cluster, ec2_key_name must be configured.
+  # You can create a key pair in page https://console.aws.amazon.com/ec2#KeyPairs and download the key file.
+  # ec2_key_name: '[ec2_key_pair_name]'
+
+spark_config:
+  # Application name
+  app_name: 'my spark app'
+  # Master URL to connect to
+  # e.g., spark_master: 'spark://host:port', or spark_master: 'yarn'
+  spark_master: 'local'
+  # Executor environment variables
+  # e.g., executor_env: {'PYTHONPATH': '/home/path'}
+  executor_env: {}
+  # Jar files to be uploaded to the cluster and added to the classpath
+  # e.g., spark_jars: ['/home/path/example1.jar']
+  spark_jars: []
+  # Path where Spark is installed on worker nodes
+  # e.g. spark_home: '/usr/lib/spark'
+  spark_home:
+  # List of key-value pairs to be set in SparkConf
+  # e.g., others: {'spark.executor.memory': '4g', 'spark.executor.cores': '2'}
+  others: {}
+  # Whether to create custom SparkSession via code and set in kwargs['context']
+  use_custom_session: false
+  # The variable name to set in kwargs['context'],
+  # e.g. kwargs['context']['spark'] = spark_session
+  custom_session_var_name: 'spark'
+
+help_improve_mage: true
+notification_config:
+  alert_on:
+  - trigger_failure
+  - trigger_passed_sla
+  slack_config:
+    webhook_url: "{{ env_var('MAGE_SLACK_WEBHOOK_URL') }}"
+  teams_config:
+    webhook_url: "{{ env_var('MAGE_TEAMS_WEBHOOK_URL') }}"
+project_uuid: homework_03
diff --git a/mlops/homework_03/pipelines/__init__.py b/mlops/homework_03/pipelines/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/pipelines/data__preparation/__init__.py b/mlops/homework_03/pipelines/data__preparation/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/pipelines/data__preparation/interactions.yaml b/mlops/homework_03/pipelines/data__preparation/interactions.yaml
new file mode 100644
index 000000000..a1d40f831
--- /dev/null
+++ b/mlops/homework_03/pipelines/data__preparation/interactions.yaml
@@ -0,0 +1,2 @@
+blocks: {}
+layout: []
diff --git a/mlops/homework_03/pipelines/data__preparation/metadata.yaml b/mlops/homework_03/pipelines/data__preparation/metadata.yaml
new file mode 100755
index 000000000..6f012911e
--- /dev/null
+++ b/mlops/homework_03/pipelines/data__preparation/metadata.yaml
@@ -0,0 +1,80 @@
+blocks:
+- all_upstream_blocks_executed: true
+  color: null
+  configuration:
+    file_source:
+      path: homework_03/data_loaders/ingest.py
+  downstream_blocks:
+  - prepare
+  executor_config: null
+  executor_type: local_python
+  has_callback: false
+  language: python
+  name: Ingest
+  retry_config: null
+  status: executed
+  timeout: null
+  type: data_loader
+  upstream_blocks: []
+  uuid: ingest
+- all_upstream_blocks_executed: true
+  color: null
+  configuration:
+    file_source:
+      path: homework_03/transformers/prepare.py
+  downstream_blocks:
+  - build
+  executor_config: null
+  executor_type: local_python
+  has_callback: false
+  language: python
+  name: Prepare
+  retry_config: null
+  status: executed
+  timeout: null
+  type: transformer
+  upstream_blocks:
+  - ingest
+  uuid: prepare
+- all_upstream_blocks_executed: true
+  color: null
+  configuration:
+    file_source:
+      path: homework_03/data_exporters/build.py
+  downstream_blocks: []
+  executor_config: null
+  executor_type: local_python
+  has_callback: false
+  language: python
+  name: Build
+  retry_config: null
+  status: updated
+  timeout: null
+  type: data_exporter
+  upstream_blocks:
+  - prepare
+  uuid: build
+cache_block_output_in_memory: false
+callbacks: []
+concurrency_config: {}
+conditionals: []
+created_at: '2024-06-08 08:12:33.660390+00:00'
+data_integration: null
+description: Load data and perform feature engineering
+executor_config: {}
+executor_count: 1
+executor_type: null
+extensions: {}
+name: Data  preparation
+notification_config: {}
+remote_variables_dir: null
+retry_config: {}
+run_pipeline_in_one_process: false
+settings:
+  triggers: null
+spark_config: {}
+tags: []
+type: python
+uuid: data__preparation
+variables_dir: /home/src/mage_data/homework_03
+widgets: []
diff --git a/mlops/homework_03/pipelines/example_pipeline/__init__.py b/mlops/homework_03/pipelines/example_pipeline/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/pipelines/example_pipeline/metadata.yaml b/mlops/homework_03/pipelines/example_pipeline/metadata.yaml
new file mode 100755
index 000000000..c04cfbcf8
--- /dev/null
+++ b/mlops/homework_03/pipelines/example_pipeline/metadata.yaml
@@ -0,0 +1,30 @@
+blocks:
+- all_upstream_blocks_executed: true
+  downstream_blocks:
+  - fill_in_missing_values
+  name: load_titanic
+  status: not_executed
+  type: data_loader
+  upstream_blocks: []
+  uuid: load_titanic
+- all_upstream_blocks_executed: true
+  downstream_blocks:
+  - export_titanic_clean
+  name: fill_in_missing_values
+  status: not_executed
+  type: transformer
+  upstream_blocks:
+  - load_titanic
+  uuid: fill_in_missing_values
+- all_upstream_blocks_executed: true
+  downstream_blocks: []
+  name: export_titanic_clean
+  status: not_executed
+  type: data_exporter
+  upstream_blocks:
+  - fill_in_missing_values
+  uuid: export_titanic_clean
+name: example_pipeline
+type: python
+uuid: example_pipeline
+widgets: []
diff --git a/mlops/homework_03/pipelines/sklearn_training/__init__.py b/mlops/homework_03/pipelines/sklearn_training/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/pipelines/sklearn_training/metadata.yaml b/mlops/homework_03/pipelines/sklearn_training/metadata.yaml
new file mode 100755
index 000000000..a05fec5ca
--- /dev/null
+++ b/mlops/homework_03/pipelines/sklearn_training/metadata.yaml
@@ -0,0 +1,6 @@
+created_at: '2024-06-08 20:49:13.470524+00:00'
+description: Pipepline for training a LinearRegression model
+name: sklearn training
+tags: []
+type: python
+uuid: sklearn_training
diff --git a/mlops/homework_03/requirements.txt b/mlops/homework_03/requirements.txt
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/scratchpads/__init__.py b/mlops/homework_03/scratchpads/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/transformers/__init__.py b/mlops/homework_03/transformers/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/homework_03/transformers/fill_in_missing_values.py b/mlops/homework_03/transformers/fill_in_missing_values.py
new file mode 100755
index 000000000..b9761c3e2
--- /dev/null
+++ b/mlops/homework_03/transformers/fill_in_missing_values.py
@@ -0,0 +1,45 @@
+from pandas import DataFrame
+import math
+
+if 'transformer' not in globals():
+    from mage_ai.data_preparation.decorators import transformer
+if 'test' not in globals():
+    from mage_ai.data_preparation.decorators import test
+
+def select_number_columns(df: DataFrame) -> DataFrame:
+    return df[['Age', 'Fare', 'Parch', 'Pclass', 'SibSp', 'Survived']]
+
+
+def fill_missing_values_with_median(df: DataFrame) -> DataFrame:
+    for col in df.columns:
+        values = sorted(df[col].dropna().tolist())
+        median_value = values[math.floor(len(values) / 2)]
+        df[[col]] = df[[col]].fillna(median_value)
+    return df
+
+
+@transformer
+def transform_df(df: DataFrame, *args, **kwargs) -> DataFrame:
+    """
+    Template code for a transformer block.
+
+    Add more parameters to this function if this block has multiple parent blocks.
+    There should be one parameter for each output variable from each parent block.
+
+    Args:
+        df (DataFrame): Data frame from parent block.
+
+    Returns:
+        DataFrame: Transformed data frame
+    """
+    # Specify your transformation logic here
+
+    return fill_missing_values_with_median(select_number_columns(df))
+
+
+@test
+def test_output(df) -> None:
+    """
+    Template code for testing the output of the block.
+    """
+    assert df is not None, 'The output is undefined'
diff --git a/mlops/homework_03/transformers/prepare.py b/mlops/homework_03/transformers/prepare.py
new file mode 100644
index 000000000..847578579
--- /dev/null
+++ b/mlops/homework_03/transformers/prepare.py
@@ -0,0 +1,38 @@
+import pandas as pd
+# from mlops.homework_03.data_loaders import ingest
+
+if 'transformer' not in globals():
+    from mage_ai.data_preparation.decorators import transformer
+
+
+@transformer
+def transform(data, *args, **kwargs):
+    """
+    Template code for a transformer block.
+
+    Add more parameters to this function if this block has multiple parent blocks.
+    There should be one parameter for each output variable from each parent block.
+
+    Args:
+        data: The output from the upstream parent block
+        args: The output from any additional upstream blocks (if applicable)
+
+    Returns:
+        Anything (e.g. data frame, dictionary, array, int, str, etc.)
+    """
+    # Specify your transformation logic here
+    # def read_dataframe(filename):
+    df = data
+
+    df.tpep_dropoff_datetime = pd.to_datetime(df.tpep_dropoff_datetime)
+    df.tpep_pickup_datetime = pd.to_datetime(df.tpep_pickup_datetime)
+
+    df['duration'] = df.tpep_dropoff_datetime - df.tpep_pickup_datetime
+    df.duration = df.duration.dt.total_seconds() / 60
+
+    df = df[(df.duration >= 1) & (df.duration <= 60)]
+
+    categorical = ['PULocationID', 'DOLocationID']
+    df[categorical] = df[categorical].astype(str)
+    
+    return df
diff --git a/mlops/homework_03/utils/__init__.py b/mlops/homework_03/utils/__init__.py
new file mode 100755
index 000000000..e69de29bb
diff --git a/mlops/metadata.yaml b/mlops/metadata.yaml
index 4eb3b7742..cc0dcfee9 100644
--- a/mlops/metadata.yaml
+++ b/mlops/metadata.yaml
@@ -15,3 +15,4 @@ features:
   operation_history: true
   polars: true
 help_improve_mage: true
+project_uuid: 8a1d9ffcca6e42fa98d38f4b43c70ece
diff --git a/mlops/requirements.txt b/mlops/requirements.txt
index 5c611efcf..b9de29417 100755
--- a/mlops/requirements.txt
+++ b/mlops/requirements.txt
@@ -9,3 +9,4 @@ scikit-learn
 seaborn
 shap
 xgboost
+joblib
diff --git a/mlops/settings.yaml b/mlops/settings.yaml
index 48b62b147..32fb040be 100644
--- a/mlops/settings.yaml
+++ b/mlops/settings.yaml
@@ -1,4 +1,6 @@
 projects:
+  homework_03:
+    path: homework_03
   unit_0_setup: {}
   unit_1_data_preparation: {}
   unit_2_training: {}