discovery-engine-api 0.1.0

Python SDK for the Discovery Engine API

Discovery Engine Python API

The Discovery Engine Python API provides a simple programmatic interface to run analyses via Python, offering an alternative to using the web dashboard. Instead of uploading datasets and configuring analyses through the UI, you can automate your discovery workflows directly from your Python code or scripts.

All analyses run through the API are fully integrated with your Discovery Engine account. Results are automatically displayed in the dashboard, where you can view detailed reports, explore patterns, and share findings with your team. Your account management, credit balance, and subscription settings are all handled through the dashboard—the API is simply a convenient interface for programmatic access to the same powerful discovery engine.

Installation

pip install discovery-engine-api

For pandas DataFrame support:

pip install discovery-engine-api[pandas]

Quick Start

from discovery import Engine

# Initialize engine
engine = Engine(api_key="your-api-key")

# Run analysis on a dataset and wait for results
result = engine.run(
    file="data.csv",
    target_column="diagnosis",
    mode="fast",
    description="Rare diseases dataset",
    wait=True  # Wait for completion and return full results
)

print(f"Run ID: {result.run_id}")
print(f"Status: {result.status}")
print(f"Found {len(result.patterns)} patterns")

Examples

Working with Pandas DataFrames

import pandas as pd
from discovery import Engine

df = pd.read_csv("data.csv")
# or create DataFrame directly

engine = Engine(api_key="your-api-key")
result = engine.run(
    file=df,  # Pass DataFrame directly
    target_column="outcome",
    column_descriptions={
        "age": "Patient age in years",
        "heart rate": None
    },
    wait=True
)

Async Workflow

import asyncio
from discovery import Engine

async def run_analysis():
    async with Engine(api_key="your-api-key") as engine:
        # Start analysis without waiting
        result = await engine.run_async(
            file="data.csv",
            target_column="target",
            wait=False
        )
        print(f"Started run: {result.run_id}")

        # Later, get results
        result = await client.get_results(result.run_id)
        
        # Or wait for completion
        result = await client.wait_for_completion(result.run_id, timeout=600)
        return result

result = asyncio.run(run_analysis())

Configuration Options

The run() and run_async() methods accept the following parameters:

Parameter	Type	Default	Description
file	str, Path, or DataFrame	Required	Dataset file path or pandas DataFrame
target_column	str	Required	Name of column to predict
mode	"fast" / "deep"	"fast"	Analysis depth
title	str	None	Optional dataset title
description	str	None	Optional dataset description
column_descriptions	Dict[str, str]	None	Optional column name -> description mapping
task	str	None	Override auto-detected task type: "regression", "binary_classification", or "multiclass_classification"
visibility	"public" / "private"	"public"	Dataset visibility (private requires credits)
timeseries_groups	List[Dict]	None	Timeseries column groups for feature extraction
auto_report_use_llm_evals	bool	True	Use LLM for pattern descriptions
author	str	None	Optional dataset author attribution
source_url	str	None	Optional source URL for dataset
wait	bool	False	Wait for analysis to complete and return full results
wait_timeout	float	None	Maximum seconds to wait for completion (only if wait=True)

Credits and Pricing

• Public datasets: Free (0 credits required)
• Private datasets:
  • Fast mode: 1 credit per MB
  • Deep mode: 3 credits per MB

If you don't have enough credits for a private run, the SDK will raise an httpx.HTTPStatusError with an error message like:

Insufficient credits. You need X credits but only have Y available.

Solutions:

1. Make your dataset public (set visibility="public") - completely free
2. Visit https://disco.leap-labs.com/account to:
   • Purchase additional credits
   • Upgrade to a subscription plan that includes more credits

Return Value

The run() and run_async() methods return an EngineResult object with the following fields:

EngineResult

@dataclass
class EngineResult:
    # Identifiers
    run_id: str                    # Unique run identifier
    report_id: Optional[str]       # Report ID (if report created)
    status: str                    # "pending", "processing", "completed", "failed"
    
    # Dataset metadata
    dataset_title: Optional[str]           # Dataset title
    dataset_description: Optional[str]    # Dataset description
    total_rows: Optional[int]              # Number of rows in dataset
    target_column: Optional[str]           # Name of target column
    task: Optional[str]                    # "regression", "binary_classification", or "multiclass_classification"
    
    # LLM-generated summary
    summary: Optional[Summary]             # Summary object with overview, insights, etc.
    
    # Discovered patterns
    patterns: List[Pattern]                 # List of discovered patterns
    
    # Column/feature information
    columns: List[Column]                  # List of columns with statistics and importance
    
    # Correlation matrix
    correlation_matrix: List[CorrelationEntry]  # Feature correlations
    
    # Global feature importance
    feature_importance: Optional[FeatureImportance]  # Feature importance scores
    
    # Job tracking
    job_id: Optional[str]           # Job ID for tracking processing
    job_status: Optional[str]      # Job status
    error_message: Optional[str]   # Error message if analysis failed

Summary

@dataclass
class Summary:
    overview: str                          # High-level explanation of findings
    key_insights: List[str]                # List of main takeaways
    novel_patterns: PatternGroup           # Novel pattern explanations
    surprising_findings: PatternGroup      # Surprising findings
    statistically_significant: PatternGroup  # Statistically significant patterns
    data_insights: Optional[DataInsights]  # Important features, correlations
    selected_pattern_id: Optional[str]     # ID of selected pattern

Pattern

@dataclass
class Pattern:
    id: str                                # Pattern identifier
    task: str                              # Task type
    target_column: str                     # Target column name
    direction: str                         # "min" or "max"
    p_value: float                         # Statistical p-value
    conditions: List[Dict]                 # Pattern conditions (continuous, categorical, datetime)
    lift_value: float                      # Lift value (how much the pattern increases/decreases target)
    support_count: int                     # Number of rows matching pattern
    support_percentage: float              # Percentage of rows matching pattern
    pattern_type: str                      # "validated" or "speculative"
    novelty_type: str                      # "novel" or "confirmatory"
    target_score: float                    # Target score for this pattern
    description: str                       # Human-readable description
    novelty_explanation: str               # Explanation of novelty
    target_class: Optional[str]            # Target class (for classification)
    target_mean: Optional[float]           # Target mean (for regression)
    target_std: Optional[float]            # Target standard deviation
    citations: List[Dict]                  # Academic citations

Column

@dataclass
class Column:
    id: str                                # Column identifier
    name: str                              # Column name
    display_name: str                      # Display name
    type: str                              # "continuous" or "categorical"
    data_type: str                         # "int", "float", "string", "boolean", "datetime"
    enabled: bool                          # Whether column is enabled
    description: Optional[str]              # Column description
    
    # Statistics
    mean: Optional[float]                  # Mean value
    median: Optional[float]                 # Median value
    std: Optional[float]                   # Standard deviation
    min: Optional[float]                   # Minimum value
    max: Optional[float]                   # Maximum value
    iqr_min: Optional[float]               # IQR minimum
    iqr_max: Optional[float]               # IQR maximum
    mode: Optional[str]                    # Mode value
    approx_unique: Optional[int]           # Approximate unique count
    null_percentage: Optional[float]      # Percentage of null values
    
    # Feature importance
    feature_importance_score: Optional[float]  # Feature importance score

FeatureImportance

@dataclass
class FeatureImportance:
    kind: str                              # Feature importance type: "global" 
    baseline: float                        # Baseline model output
    scores: List[FeatureImportanceScore]   # List of feature scores

CorrelationEntry

@dataclass
class CorrelationEntry:
    feature_x: str                         # First feature name
    feature_y: str                         # Second feature name
    value: float                           # Correlation value (-1 to 1)

Pattern

@dataclass
class Pattern:
    id: str
    task: str
    target_column: str
    direction: str  # "min" or "max"
    p_value: float
    conditions: List[Dict]  # Continuous, categorical, or datetime conditions
    lift_value: float
    support_count: int
    support_percentage: float
    pattern_type: str  # "validated" or "speculative"
    novelty_type: str  # "novel" or "confirmatory"
    target_score: float
    description: str
    novelty_explanation: str
    target_class: Optional[str]
    target_mean: Optional[float]
    target_std: Optional[float]
    citations: List[Dict]