esenthil2018

url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data'
column_names = ['MPG', 'Cylinders', 'Displacement', 'Horsepower', 'Weight',
                'Acceleration', 'Model Year', 'Origin']

raw_dataset = pd.read_csv(url, names=column_names,
                          na_values='?', comment='\t',
                          sep=' ', skipinitialspace=True)

esenthil2018

%%capture
import IPython

if (IPython.version_info[0] < 7):
  !pip -q install ipython --upgrade
  # To load the updated ipython that we have just installed, 
  # we need to restart the runtime. The exit() command allows 
  # us to stop the current runtime, and executing the cell after 
  # it would restart the runtime.
  exit()

esenthil2018

import os
directory = lineapy.to_pipeline(
    [train_art.name,test_art.name,y_art.name, model_art.name], 
    framework = 'AIRFLOW',
    pipeline_name = "titanic_pipeline",
    dependencies = {'titanic_pipeline_decision_tree_titanic':{'titanic_pipeline_train_data','titanic_pipeline_test_data','titanic_pipeline_y'}},
    output_dir = os.environ.get("AIRFLOW_HOME","~/airflow")+"/dags")

esenthil2018

train_art = lineapy.get("train_data")
train_art
#LineaArtifact(name='train_data', _version=0)
test_art = lineapy.get("test_data")
test_art
#LineaArtifact(name='test_data', _version=0)
y_art = lineapy.get("y")
y_art
#LineaArtifact(name='y', _version=0)
model_art = lineapy.get("decision_tree_titanic")

esenthil2018

model_artifact = lineapy.save(decision_tree, 'decision_tree_titanic')

esenthil2018

#RandomeForestClassifer
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators=100, max_depth=5, random_state=1)
model.fit(X, y)
predictions = model.predict(X_test)
model.score(X, y)
acc_random_forest = round(model.score(X, y) * 100, 2)
acc_random_forest

# Gaussian Naive Bayes

esenthil2018

# Store the variable as an artifact
train_artifact = lineapy.save(X, "train_data")
# Check object type
print(type(train_artifact))
# Store the variable as an artifact
test_artifact = lineapy.save(X_test, "test_data")
# Check object type
print(type(test_artifact))
# Store the variable as an artifact
y_artifact = lineapy.save(y, "y")

esenthil2018

---
- name: Update web servers
  hosts: webservers
  remote_user: root

  tasks:
  - name: Ensure apache is at the latest version
    ansible.builtin.yum:
      name: httpd
      state: latest

esenthil2018

Resources:
  Ec2Instance:
    Type: 'AWS::EC2::Instance'
    Properties:
      SecurityGroups:
        - !Ref InstanceSecurityGroup
      KeyName: mykey
      ImageId: ''
  InstanceSecurityGroup:
    Type: 'AWS::EC2::SecurityGroup'

esenthil2018

version: "3.9"  # optional since v1.27.0
services:
  web:
    build: .
    ports:
      - "5000:5000"
    volumes:
      - .:/code
      - logvolume01:/var/log
    links: