aletheia

Keybase proof

I hereby claim:

• I am aletheia on github.
• I am aletheia1982 (https://keybase.io/aletheia1982) on keybase.
• I have a public key ASDD8nTTwlydf9VE8FzkqvXEMnJa5rNtaie-qMq-FqLhLQo

To claim this, I am signing this object:

aletheia

data:
{
   "message":{
      "id":"a49b7544-f0eb-43eb-9e56-f28b2961bf19",
      "role":"assistant",
      "user":null,
      "create_time":null,
      "update_time":null,
      "content":{
         "content_type":"text",

aletheia

data: 
{
  "message": {
    "id": "a49b7544-f0eb-43eb-9e56-f28b2961bf19", 
    "role": "assistant", 
    "user": null, 
    "create_time": null, 
    "update_time": null, 
    "content": {
      "content_type": "text", 

aletheia

{
	"user": {
		"id": "user-myuserid",
		"name": "Luca Bianchi",
		"email": "luca.bianchi@myemail.com",
		"image": "https://path/to/user/image",
		"picture": "https://path/to/profile/picture",
		"groups": [
			"codex",
			"sunset-search-endpoint",

aletheia

{
  "action": "variant",
  "messages": [
    {
      "id": "b866650c-4797-4fc9-91dc-962af79ff369",
      "role": "user",
      "content": {
        "content_type": "text",
        "parts": [
          "Who are you?"

aletheia

AWSTemplateFormatVersion: '2010-09-09'
Transform: AWS::Serverless-2016-10-31
Description: >
  AWS Lambda Rust ML -- Example showing how to use Rust with AWS Lambda to build a customer churn predictor

Globals:
  Function:

Resources:
  S3ModelBucket:

aletheia

#[derive(Deserialize, Serialize)]
struct User {
    customer_id: String,
    senior_citizen: i32,
    #[serde(default, rename = "churnProbability")]
    churn_probability: Option<f64>,
    #[serde(rename = "MonthlyCharges")]
    monthly_charges: f64,
    #[serde(rename = "TotalCharges")]
    total_charges: f64,

aletheia

impl From<&User> for Vec<f64> {
    fn from(user: &User) -> Vec<f64> {
        vec![
            user.senior_citizen as f64,
            user.tenure as f64,
            user.monthly_charges,
            user.total_charges,
            // ... more fields are omitted for brevity
            ]
    }

aletheia

    def validation_step(self, batch, batch_idx):
        ''' Prforms model validation computing cross entropy for predictions and labels
        '''
        x, labels = batch
        prediction = self.forward(x)
        return {
            'val_loss': F.cross_entropy(prediction, labels)
        }
    
    def validation_epoch_end(self, outputs):

aletheia

    def training_step(self, batch, batch_idx):
        '''Called for every training step, uses NLL Loss to compute training loss, then logs and sends back 
        logs parameter to Trainer to perform backpropagation
        '''
        
        # Get input and output from batch
        x, labels = batch
        
        # Compute prediction through the network
        prediction = self.forward(x)