Using the Turn-On Models

Installation

We recommend using pip, poetry, or uv to install the package.

$pip install conductorquantum

Authentication

The SDK requires an API key for authentication. Sign in and create a new API key. Remember, your API key is your access secret—keep it safe with environment variables.

Using environment variables:

Python
1from dotenv import load_dotenv
2import os
3from conductorquantum import ConductorQuantum
4
5# Load API key from .env file
6load_dotenv()
7TOKEN = os.getenv("CONDUCTOR_API_KEY")
8
9# Initialize client
10client = ConductorQuantum(token=TOKEN)

Or provide the API key directly:

Python
1from conductorquantum import ConductorQuantum
2
3# Initialize client with API key
4client = ConductorQuantum(token="YOUR_API_KEY")

Usage Examples

Using the Turn-On Classifier

The Turn-On Classifier is a model that can classify a given current measurement as either in the Turn-On regime or not.

You can download an example file to follow along with the example:

Python
1from dotenv import load_dotenv
2import os
3import numpy as np
4from conductorquantum import ConductorQuantum
5
6
7# Load API key from .env file
8load_dotenv()
9TOKEN = os.getenv("CONDUCTOR_API_KEY")
10
11# Initialize client
12client = ConductorQuantum(token=TOKEN)
13
14# Load Turn-on data (current measurement)
15data = np.load("turn-on-classifier-v0.npy") # shape (n, )
16
17# Detect Turn-on
18result = client.models.execute(
19 model="turn-on-classifier-v0",
20 data=data
21)
22
23# Access the classification result
24is_turn_on = result.output["classification"]
25print(f"Is turn-on: {is_turn_on}")
Output
1Is turn-on: True

Using the Turn-On Parameter Extractor

The Turn-On Parameter Extractor is a model that can extract the parameters of a given current measurement.

You can download an example file to follow along with the example:

Python
1from dotenv import load_dotenv
2import os
3import numpy as np
4from conductorquantum import ConductorQuantum
5
6
7# Load API key from .env file
8load_dotenv()
9TOKEN = os.getenv("CONDUCTOR_API_KEY")
10
11# Initialize client
12client = ConductorQuantum(token=TOKEN)
13
14# Load Turn-on data (current measurement)
15data = np.load("turn-on-parameter-extractor-v0.npy") # shape (n, )
16
17# Detect Turn-on
18result = client.models.execute(
19 model="turn-on-parameter-extractor-v0",
20 data=data
21)
22
23# Access the peak locations (indices)
24threshold_index = result.output["threshold_idx"]
25print(f"Threshold index: {threshold_index}")
Output
1Threshold index: 52

Plotting the Output

Python
1import matplotlib.pyplot as plt
2
3plt.figure(figsize=(10, 5), dpi=300)
4plt.plot(example_input, 'k-')
5plt.axvline(x=result_api.output["threshold_idx"], color='b', linestyle='--', label='Threshold Index')
6plt.xlabel('Voltages (Indices)')
7plt.ylabel('Current (a.u.)')
8plt.legend()
9plt.show('turn-on-parameter-extractor.png')
Turn-on Parameter Extractor
Turn-on Parameter Extractor v0 Output

Data Requirements

One-dimensional Current Data

  • Shape: (n, )
  • 1D array of current values

Important Notes for Voltage-Current Data

  • The array must be of shape (n, ) where n is the number of current values in the measurement.
  • Analysis is outputted in terms of indices of the input array.
  • The models automatically handle scaling and normalization internally.
  • For best results, ensure your data has sufficient resolution in regions of interest.