用AI大模型将CSV文件转为图谱，发现数据间关系，以健康医疗场景为例

import numpy as np
import pandas as pd
from neo4j_runway import Discovery, GraphDataModeler, IngestionGenerator, LLM, PyIngest
from IPython.display import display, Markdown, Image

load_dotenv()
OPENAI_API_KEY = os.getenv('sk-openaiapikeyhere')
NEO4J_URL = os.getenv('neo4j+s://your.databases.neo4j.io')
NEO4J_PASSWORD = os.getenv('yourneo4jpassword')

disease_df = pd.read_csv('/home/user/Disease_symptom.csv')
disease_df

disease_df[disease_df['Difficulty Breathing'] == 'Yes']

disease_df.columns = disease_df.columns.str.strip()
for i in disease_df.columns:
    disease_df[i] = disease_df[i].astype(str)
disease_df.to_csv('/home/user/disease_prepared.csv', index=False)

disc = Discovery(llm=llm, user_input=DATA_DESCRIPTION, data=disease_df)
disc.run()

# 实例化图数据建模器
gdm = GraphDataModeler(llm=llm, discovery=disc)
# 生成模型
gdm.create_initial_model()
# 可视化数据模型
gdm.current_model.visualize()

gdm.iterate_model(user_corrections='''
Let's think step by step. Please make the following updates to the data model:
1. Remove the relationships between Patient and Disease, between Patient and Symptom and between Patient and Outcome.
2. Change the Patient node into Demographics.
3. Create a relationship HAS_DEMOGRAPHICS from Disease to Demographics.
4. Create a relationship HAS_SYMPTOM from Disease to Symptom. If the Symptom value is No, remove this relationship.
5. Create a relationship HAS_LAB from Disease to HealthIndicator.
6. Create a relationship HAS_OUTCOME from Disease to Outcome.
''')

from IPython.display import Image, display
gdm.current_model.visualize().render('output', format='png')
img = Image('output.png', width=1200)  # 调整宽度
display(img)

# 实例化数据摄取生成器
gen = IngestionGenerator(
    data_model=gdm.current_model,
    username="neo4j",
    password='yourneo4jpasswordhere',
    uri='neo4j+s://123654888.databases.neo4j.io',
    database="neo4j",
    csv_dir="/home/user/",
    csv_name="disease_prepared.csv"
)

# 创建摄取 YAML
pyingest_yaml = gen.generate_pyingest_yaml_string()

# 保存本地 YAML 副本
gen.generate_pyingest_yaml_file(file_name="disease_prepared")

PyIngest(yaml_string=pyingest_yaml, dataframe=disease_df)

import warnings
import json
from langchain_community.graphs import Neo4jGraph

with warnings.catch_warnings():
    warnings.simplefilter('ignore')

NEO4J_USERNAME = "neo4j"
NEO4J_DATABASE = 'neo4j'
NEO4J_URI = 'neo4j+s://1236547.databases.neo4j.io'
NEO4J_PASSWORD = 'yourneo4jdatabasepasswordhere'

kg = Neo4jGraph(
    url=NEO4J_URI,
    username=NEO4J_USERNAME,
    password=NEO4J_PASSWORD,
    database=NEO4J_DATABASE
)
kg.refresh_schema()
print(textwrap.fill(kg.schema, 60))
schema = kg.schema

from langchain.prompts.prompt import PromptTemplate
from langchain.chains import GraphCypherQAChain
from langchain.llms import VertexAI

# Initialize Vertex AI
vertexai.init(project="your-project", location="us-west4")
llm = VertexAI(model="gemini-1.5-flash")

prompt_template = """
Let's think step by step:

Step 1: Task:
Generate an effective and concise Cypher statement with less than 256 characters to query a graph database.
Do not comment the code.

Step 2: Get to know the database schema: {schema}

Step 3: Instructions:
- In the cypher query, ONLY USE the provided relationship types and properties that appear in the schema AND in the user question.
- In the cypher query, do not use any other relationship types or properties in the user's question that are not contained in the provided schema.
- Regarding Age, NEVER work with the age itself. For example: 24 years old, use interval: more than 20 years old.
- USE ONLY ONE statement for Age, always use 'greater than', never 'less than' or 'equal'.
- DO NOT USE property keys that are not in the database.

Step 4: Examples:
Here are a few examples of generated Cypher statements for particular questions:

4.1 Which diseases present high blood pressure?
MATCH (d:Disease)
MATCH (d)-[r:HAS_LAB]->(l)
WHERE l.bloodPressure = 'High'
RETURN d.name

4.2 Which diseases present indicators as high blood pressure?
MATCH (d:Disease)
MATCH (d)-[r:HAS_LAB]->(l)
MATCH (d)-[r2:HAS_OUTCOME]->(o)
WHERE l.bloodPressure = 'High' AND o.result='Positive'
RETURN d, properties(d) AS disease_properties, r, properties(r) AS relationship_properties, l, properties(l) AS lab_properties

4.3 What is the name of a disease of the elderly where the patient presents high blood pressure, high cholesterol, fever, fatigue
MATCH (d:Disease)
MATCH (d)-[r1:HAS_LAB]->(lab)
MATCH (d)-[r2:HAS_SYMPTOM]->(symptom)
MATCH (symptom)-[r3:HAS_DEMOGRAPHICS]->(demo)
WHERE lab.bloodPressure = 'High' AND lab.cholesterolLevel = 'High' AND symptom.fever = 'Yes' AND symptom.fatigue = 'Yes' AND TOINTEGER(demo.age) >40
RETURN d.name

4.4 What disease gives you fever, fatigue, no cough, no short breathe in people with high cholesterol?
MATCH (d:Disease)-[r:HAS_SYMPTOM]->(s:Symptom)
WHERE s.fever = 'Yes' AND s.fatigue = 'Yes' AND s.difficultyBreathing = 'No' AND s.cough = 'No'
MATCH (d:Disease)-[r1:HAS_LAB]->(lab:HealthIndicator)
MATCH (d)-[r2:HAS_OUTCOME]->(o:Outcome)
WHERE lab.cholesterolLevel='High' AND o.result='Positive'
RETURN d, properties(d) AS disease_properties, r, properties(r) AS relationship_properties

Step 5. These are the values allowed for each entity:
- Fever: Indicates whether the patient has a fever (Yes/No).
- Cough: Indicates whether the patient has a cough (Yes/No).
- Fatigue: Indicates whether the patient experiences fatigue (Yes/No).
- Difficulty Breathing: Indicates whether the patient has difficulty breathing (Yes/No).
- Age: The age of the patient in years.
- Gender: The gender of the patient (Male/Female).
- Blood Pressure: The blood pressure level of the patient (Normal/High).
- Cholesterol Level: The cholesterol level of the patient (Normal/High).
- Outcome Variable: The outcome variable indicating the result of the diagnosis or assessment for the specific disease (Positive/Negative).

Step 6: Answer the question {question}.
"""

cypher_prompt = PromptTemplate(
    input_variables=["schema", "question"],
    template=prompt_template
)

cypherChain = GraphCypherQAChain.from_llm(
    VertexAI(temperature=0.1),
    graph=kg,
    verbose=True,
    cypher_prompt=cypher_prompt,
    top_k=10  # 这个值可以调整
)

cypherChain.run("""
Patient Information:
Jane Doe, a 58-year-old female, was admitted on June 15, 2024.

Chief Complaint and History of Present Illness:
Jane reported a high fever up to 104°F, body pain, and a rash,
starting five days prior to admission.

Past Medical History:
Jane has no significant past medical history and no known allergies.

Physical Examination:
Jane's temperature was 102.8°F, heart rate 110 bpm, blood pressure 100/70 mmHg, and respiratory rate 20 breaths per minute. No petechiae or purpura were noted.

What disease may she have?
""")