pip install discovery-engine-api

# Step 1: request verification code (no password, no card)
curl -X POST https://disco.leap-labs.com/api/signup \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com"}'

# Step 2: submit code from email → get key
curl -X POST https://disco.leap-labs.com/api/signup/verify \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com", "code": "123456"}'
# → {"key": "disco_...", "credits": 10, "tier": "free_tier"}

from discovery import Engine

engine = Engine(api_key="disco_...")
result = await engine.discover(
    file="data.csv",
    target_column="outcome",
)

for pattern in result.patterns:
    if pattern.p_value < 0.05 and pattern.novelty_type == "novel":
        print(f"{pattern.description} (p={pattern.p_value:.4f})")

print(f"Explore: {result.report_url}")

Pattern(
    description="When humidity is between 72–89% AND wind speed is below 12 km/h, "
                "crop yield increases by 34% above the dataset average",
    conditions=[
        {"type": "continuous", "feature": "humidity_pct",
         "min_value": 72.0, "max_value": 89.0},
        {"type": "continuous", "feature": "wind_speed_kmh",
         "min_value": 0.0, "max_value": 12.0},
    ],
    p_value=0.003,              # FDR-corrected
    novelty_type="novel",
    novelty_explanation="Published studies examine humidity and wind speed as independent "
                        "predictors, but this interaction effect — where low wind amplifies "
                        "the benefit of high humidity within a specific range — has not been "
                        "reported in the literature.",
    citations=[
        {"title": "Effects of relative humidity on cereal crop productivity",
         "authors": ["Zhang, L.", "Wang, H."], "year": "2021",
         "journal": "Journal of Agricultural Science"},
    ],
    target_change_direction="max",
    abs_target_change=0.34,     # 34% increase
    support_count=847,          # rows matching this pattern
    support_percentage=16.9,
)

result.summary.overview
# "Disco identified 14 statistically significant patterns. 5 are novel.
#  The strongest driver is a previously unreported interaction between humidity
#  and wind speed at specific thresholds."

result.summary.key_insights
# ["Humidity × low wind speed at 72–89% humidity produces a 34% yield increase — novel.",
#  "Soil nitrogen above 45 mg/kg shows diminishing returns when phosphorus is below 12 mg/kg.",
#  ...]

await engine.discover(
    file="data.csv",           # path, Path, or pd.DataFrame
    target_column="outcome",   # column to predict/explain
    analysis_depth=2,          # 2=default, higher=deeper analysis, lower = faster and cheaper
    visibility="public",       # "public" (always free, data and report is published) or "private" (costs credits)
    column_descriptions={      # improves pattern explanations and literature context
        "bmi": "Body mass index",
        "hdl": "HDL cholesterol in mg/dL",
    },
    excluded_columns=["id", "timestamp"],  # see "Preparing your data" above
    use_llms=False,                        # Defaults to False. If True, runs are slower and more expensive, but you get smarter pre-processing, summary page, literature context and novelty assessment. Public runs always use LLMs.
    title="My dataset",
    description="...", # improves pattern explanations and literature context
)

# Submit without waiting
run = await engine.run_async(file="data.csv", target_column="outcome", wait=False)
print(f"Submitted {run.run_id}, continuing...")

# ... do other things ...

result = await engine.wait_for_completion(run.run_id, timeout=1800)

result = engine.run(file="data.csv", target_column="outcome", wait=True)
# or: pip install discovery-engine-api[jupyter] for notebook compatibility

{
  "mcpServers": {
    "discovery-engine": {
      "url": "https://disco.leap-labs.com/mcp",
      "env": { "DISCOVERY_API_KEY": "disco_..." }
    }
  }
}

estimate = await engine.estimate(file_size_mb=10.5, num_columns=25, analysis_depth=2, visibility="private")
# estimate["cost"]["credits"] → 55
# estimate["account"]["sufficient"] → True/False

| patient_id | age | bmi  | smoker | outcome |
|------------|-----|------|--------|---------|
| 001        | 52  | 28.3 | yes    | 1       |
| 002        | 34  | 22.1 | no     | 0       |
| ...        | ... | ...  | ...    | ...     |