#!/usr/bin/env python
# coding: utf-8

# # Meta functionalities of the EpiGraphDB platform

# In this notebook we show the following aspects of the EpiGraphDB platform, and how to use the API to get the information:
# 
# 1. Metadata: meta nodes and meta edges, and the overall schema.
# 2. Search for a specific node under the meta node.
# 3. Cypher: how to query the database directly using Neo4j Cypher
# 
# For detailed documentation on the API endpoints please visit:
# 
# - The Swagger interface: http://api.epigraphdb.org
# - The sections regarding API endpoints on the documentation site: http://docs.epigraphdb.org/api/api-endpoints/

# In[1]:


from pprint import pformat

import networkx as nx
import pandas as pd
import requests


# In[2]:


API_URL = "https://api.epigraphdb.org"

requests.get(f"{API_URL}/ping").json()


# ## Metadata

# Here we query for the metadata information using the endpoint `GET /meta/schema`, which will be used for downstream processing.

# In[3]:


endpoint = "/meta/schema"
params = {"graphviz": False, "plot": False}
r = requests.get(f"{API_URL}{endpoint}", params=params)
r.raise_for_status()
metadata = r.json()

# Preview of metadata information
keys = metadata.keys()
print(pformat(keys), "\n")
for key in list(keys):
    print(f"# {key}:")
    print(pformat(metadata[key])[:1000], "\n")


# ### Meta nodes
# 
# We can extract the specific meta node information as a pandas dataframe from the metadata.

# In[4]:


meta_node_df = pd.DataFrame.from_dict(metadata["nodes"], orient="index")

(
    meta_node_df.sort_index().assign(
        count=lambda df: df["count"].apply(lambda x: f"{x:,}")
    )
)


# ### Meta relationships and connections
# 
# We can also extract the meta relationship (edge) information, and the connections.

# In[5]:


meta_rel_df = pd.DataFrame.from_dict(metadata["edges"], orient="index").merge(
    pd.DataFrame.from_dict(
        {_["rel"]: _ for _ in metadata["connections"]}, orient="index"
    )[["from_node", "to_node"]],
    left_index=True,
    right_index=True,
)

(
    meta_rel_df.sort_values(by=["from_node", "to_node"]).assign(
        count=lambda df: df["count"].apply(lambda x: f"{x:,}")
    )
)


# ### Schema plot

# We can generate a network diagram of the graph db schema using `networkx`.

# In[6]:


graph = nx.from_pandas_edgelist(
    meta_rel_df, source="from_node", target="to_node"
)


# In[7]:


nx.draw(
    G=graph,
    pos=nx.kamada_kawai_layout(graph),
    with_labels=True,
    node_color="white",
)


# A detailed version of the shema plot can be obtained from the API:
# 
# ![schema_plot](http://ieu-mrbssd1.epi.bris.ac.uk:28046/meta/schema?graphviz=true&plot=true)

# ## Search for specific node

# Users can use [the explorer on the Web UI](http://dev.epigraphdb.org/explore) to search for a specific node by:
# 
# - fuzzy matching by "name" field.
# - exact matching by "ID" field if you know the its ID (e.g. the ID to a GWAS from IEU GWAS Database).
# 
# Here we show how these are done at the API level using `Gwas` nodes as an example.

# First we need to know what the "ID" and "name" fields are for the meta nodes using `GET /meta/nodes/id-name-schema`:

# In[8]:


r = requests.get(f"{API_URL}/meta/nodes/id-name-schema")
r.raise_for_status()

meta_node_fields = r.json()
meta_node_fields


# ### Fuzzy matching

# Here we search for nodes can contain "body mass index" in their traits.

# In[9]:


name = "body mass index"

r = requests.get(f"{API_URL}/meta/nodes/Gwas/search", params={"name": name})
r.raise_for_status()

print(pformat(r.json())[:3000])


# ### Exact matching

# Similarly, we can exact match a specific node by its ID.

# In[10]:


id = "ieu-a-2"

r = requests.get(f"{API_URL}/meta/nodes/Gwas/search", params={"id": id})
r.raise_for_status()

print(pformat(r.json())[:3000])


# ## Cypher (advanced)

# Advanced users that are familiar with Neo4j Cypher can query the database using Cypher directly.

# In[11]:


query = """
    MATCH (exposure:Gwas)-[mr:MR]->(outcome:Gwas) 
    WHERE exposure.trait = "Body mass index"
    RETURN exposure, outcome, mr LIMIT 2
"""

r = requests.post(f"{API_URL}/cypher", json={"query": query})
r.raise_for_status()

print(pformat(r.json())[:3000])


# Alternatively we provide an endpoint `POST /cypher/builder/plain` that assist users in querying for simple cypher queries.

# In[12]:


payload = {
    "source_meta_node": "Gwas",
    "target_meta_node": "Gwas",
    "meta_rel": "MR",
    "where": ["source_node.trait = 'Body mass index'"],
    "limit": 2,
}

r = requests.post(f"{API_URL}/cypher/builder/plain", json=payload)
r.raise_for_status()

print(pformat(r.json())[:3000])


# Again for the detailed documentation on the API endpoints please visit:
# 
# - The Swagger interface: http://api.epigraphdb.org
# - The sections regarding API endpoints on the documentation site: http://docs.epigraphdb.org/api/api-endpoints/