DataFrame Analytics

Load the full registry into a pandas DataFrame and run analytics.

Requires the analytics extra:

pip install anchorregistry[analytics]

These examples run against Sepolia testnet (network="sepolia"). To run against Base mainnet: replace configure(network="sepolia") with configure(network="base"). All function calls, record structures, and output shapes are identical across networks.

[1]:

# Cell 1 — setup
from anchorregistry import configure, get_all, to_dataframe, BASE_SEPOLIA_RPC, V1A_BASE_SEPOLIA
import pandas as pd

configure(
    network="base-sepolia",
    contract_address=V1A_BASE_SEPOLIA,
    rpc_url=BASE_SEPOLIA_RPC,  # swap for Infura / Alchemy URL for faster scans
)

[2]:

# Cell 2 — load full registry into DataFrame
df = to_dataframe(get_all())
print(f"Shape: {df.shape}")
df.dtypes

Shape: (5, 28)

[2]:

ar_id                     str
registered               bool
artifact_type_index     int64
artifact_type_name        str
tx                        str
block                   int64
registrant                str
manifest_hash             str
parent_ar_id              str
descriptor                str
title                     str
author                    str
tree_id                   str
token_commitment          str
research_doi              str
research_institution      str
research_co_authors       str
research_url              str
data_data_version         str
data_format               str
data_row_count            str
data_schema_url           str
data_url                  str
code_git_hash             str
code_license              str
code_language             str
code_version              str
code_url                  str
dtype: object

[3]:

# Cell 3 — filter by artifact type
# Type-specific data fields are flattened as {type_name}_{field_name}
# e.g. RESEARCH fields -> research_doi, research_institution, research_co_authors, research_url
research_df = df[df.artifact_type_name == "RESEARCH"]
cols = ["ar_id", "title", "research_doi", "research_institution", "research_url"]
research_df[[c for c in cols if c in research_df.columns]]

[3]:

	ar_id	title	research_doi	research_institution	research_url
0	AR-2026-dPXazj6	test sepolia anchor			https://anchorregistry.com/

[4]:

# Cell 4 — filter by registrant
registrant_df = df[df.registrant == "0xc7a7afde1177fbf0bb265ea5a616d1b8d7ed8c44"]
registrant_df[["ar_id", "artifact_type_name", "title"]]

[4]:

	ar_id	artifact_type_name	title
0	AR-2026-dPXazj6	RESEARCH	test sepolia anchor
1	AR-2026-86pNXz1	DATA	test sepolia data anchor
2	AR-2026-yPZBgoP	CODE	test show/hide toggle
3	AR-2026-A5kgam5	CODE	test hide/show toggle
4	AR-2026-L5RMQQ6	CODE	test show/hide toggle

[5]:

# Cell 5 — group by artifact type
df.groupby("artifact_type_name").size().sort_values(ascending=False)

[5]:

artifact_type_name
CODE        3
DATA        1
RESEARCH    1
dtype: int64

[6]:

# Cell 6 — tree analysis
df.groupby("tree_id").size().sort_values(ascending=False)

[6]:

tree_id
0x06d9d299e3cea4b6e4d5f332ffb1a50f191ad942ed594b1bd734873fd2e42496    1
0x3cdfef20d8c9dc273fdd8d74245833b99cc6d87a1fbd40f6cd5293dcd59beaed    1
0xaed54c1022c6f3ac608de2a26c49859f451b268d378b5e6045643f18e6afc651    1
0xb7b004b53c169d317554f22176971e3e20b0f81612f1ea54ee60ec285ea66ff8    1
0xf07140ce4deaf3b5dac859091a079f82e9656f173593feda7895d940b8fa5d13    1
dtype: int64