DEV Community

Cover image for Exploring a Twitter Network With Memgraph in a Jupyter Notebook
Memgraph profile image Memgraph
Memgraph for Memgraph

Posted on • Originally published at memgraph.com

Exploring a Twitter Network With Memgraph in a Jupyter Notebook

#python #algorithms #twitter #memgraph

Through this short tutorial, you will learn how to install Memgraph, connect to
it from a Jupyter Notebook and perform data analysis using graph algorithms. You
can find the original Jupyter Notebook in our open-source GitHub
repository.

If at any point you experience problems with this tutorial or something is
unclear to you, reach out on our Discord server.
The dataset from this tutorial is also available in the form of a Playground
sandbox
which you can query from your browser.

1. Prerequisites

For this tutorial, you will need to install:

  • Jupyter: Jupyter is necessary to run the notebook available here.
  • Docker: Docker is used because Memgraph is a native Linux application and cannot be installed on Windows and macOS.
  • GQLAlchemy: A Python OGM (Object Graph Mapper) that connects to Memgraph.
  • Pandas: A popular data science library.

2. Installation using Docker

After you install Docker, you can set up Memgraph by running:

docker run -it -p 7687:7687 -p 3000:3000 memgraph/memgraph-platform
Enter fullscreen mode Exit fullscreen mode

This command will start the download and after it finishes, run the Memgraph
container.

3. Connecting to Memgraph with GQLAlchemy

We will be using the GQLAlchemy object graph mapper (OGM) to connect to
Memgraph and execute Cypher queries easily. GQLAlchemy also serves as a
Python driver/client for Memgraph. You can install it using:

pip install gqlalchemy
Enter fullscreen mode Exit fullscreen mode

Hint: You may need to install CMake before
installing GQLAlchemy.

Maybe you got confused when I mentioned Cypher. You can think of Cypher as SQL
for graph databases. It contains many of the same language constructs like
CREATE, UPDATE, DELETE... and it's used to query the database.

from gqlalchemy import Memgraph

memgraph = Memgraph("127.0.0.1", 7687)
Enter fullscreen mode Exit fullscreen mode

Let's make sure that Memgraph is empty before we start with anything else.

memgraph.drop_database()
Enter fullscreen mode Exit fullscreen mode

Now let's see if the database is empty:

results = memgraph.execute_and_fetch(
    """
    MATCH (n) RETURN count(n) AS number_of_nodes ;
    """
)
print(next(results))
Enter fullscreen mode Exit fullscreen mode

Output:

{'number_of_nodes': 0}
Enter fullscreen mode Exit fullscreen mode

4. Define a graph schema

We are going to create Python classes that will represent our graph schema. This
way, all the objects that are returned from Memgraph will be of the correct type
if the class definition can be found.

from typing import Optional
from gqlalchemy import Field, Node, Relationship


class User(Node):
    username: str = Field(index=True, unique=True, db=memgraph)


class Retweeted(Relationship, type="RETWEETED"):
    pass
Enter fullscreen mode Exit fullscreen mode

5. Creating and returning nodes

We are going to create User nodes, save them to the database and return them
to our program:

user1 = User(username="ivan_g_despot")
user2 = User(username="supe_katarina")

user1.save(memgraph)
user2.save(memgraph)

print(user1)
print(user2)
Enter fullscreen mode Exit fullscreen mode

Output:

<User id=1874 labels={'User'} properties={'username': 'ivan_g_despot'}>
<User id=1875 labels={'User'} properties={'username': 'supe_katarina'}>
Enter fullscreen mode Exit fullscreen mode

Now, let's try to create a node using the Cypher query language. We are going to
create a node with an existing username just to check if the existence
constraint on the property username is set correctly.

try:
    results = memgraph.execute(
        """
        CREATE (:User {username: "supe_katarina"});
        """
    )
except Exception:
    print("Error: A user with the username supe_katarina is already in the database.")
Enter fullscreen mode Exit fullscreen mode

Output:

Error: A user with the username supe_katarina is already in the database.
Enter fullscreen mode Exit fullscreen mode

6. Creating and returning relationships

We are going to create a Retweeted relationship, save it to the database and
return it to our program:

retweeted = Retweeted(_start_node_id=user1._id, _end_node_id=user2._id)

retweeted.save(memgraph)

print(retweeted)
Enter fullscreen mode Exit fullscreen mode

Output:

<Retweeted id=1670 start_node_id=1874 end_node_id=1875 nodes=(1874, 1875) type=RETWEETED properties={}>
Enter fullscreen mode Exit fullscreen mode

7. Importing data from CSV files

You will need to download this file which contains a simple dataset of
scraped tweets. To import it into Memgraph, we will first need to copy it to the
Docker container where Memgraph is running. Find the CONTAINER_ID by running:

docker ps
Enter fullscreen mode Exit fullscreen mode

Copy the file with the following command (don't forget to replace
CONTAINER_ID):

docker cp scraped_tweets.csv CONTAINER_ID:scraped_tweets.csv
Enter fullscreen mode Exit fullscreen mode

We are going to see what our CSV file looks like with the help of the pandas
library. To install it, run:

pip install pandas
Enter fullscreen mode Exit fullscreen mode

Now let's see what the CSV file looks like:

import pandas as pd

data = pd.read_csv("scraped_tweets.csv")
data.head()
Enter fullscreen mode Exit fullscreen mode 
.dataframe tbody tr th:only-of-type {
    vertical-align: middle;
}

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}
Enter fullscreen mode Exit fullscreen mode

Output:

source_username target_username
0 CapeCodGiftShop RetroCEO
1 CodeAttBot LeeHillerLondon
2 BattlegroundHs getwhalinvest
3 botpokemongofr1 TrevorAllenPKMN
4 AnyaSha13331181 WORLDMUSICAWARD

Now, we can execute the Cypher command LOAD CSV, which is used for loading
data from CSV files:

memgraph.execute(
    """
    LOAD CSV FROM "/scraped_tweets.csv" WITH HEADER AS row
    MERGE (u1:User {username: row.source_username})
    MERGE (u2:User {username: row.target_username})
    MERGE (u1)-[:RETWEETED]->(u2);
    """
)
Enter fullscreen mode Exit fullscreen mode

You can think of the LOAD CSV clause as a loop that will go over every row in
the CSV file and execute the specified Cypher commands.

8. Querying the database and retrieving results

Let's make sure that our data was imported correctly by retrieving it:

results = memgraph.execute_and_fetch(
    """
    MATCH (u:User)
    RETURN u
    ORDER BY u.username DESC
    LIMIT 10;
    """
)

results = list(results)

for result in results:
    print(result["u"])
Enter fullscreen mode Exit fullscreen mode

Output:

<User id=3692 labels={'User'} properties={'username': 'zziru67'}>
<User id=3240 labels={'User'} properties={'username': 'zippydjh'}>
<User id=3725 labels={'User'} properties={'username': 'zee_row_ex'}>
<User id=3591 labels={'User'} properties={'username': 'yvonneqqm'}>
<User id=3212 labels={'User'} properties={'username': 'yujulia999'}>
<User id=2378 labels={'User'} properties={'username': 'yudhapati88'}>
<User id=2655 labels={'User'} properties={'username': 'yu100_kun'}>
<User id=2302 labels={'User'} properties={'username': 'youth_tree'}>
<User id=2432 labels={'User'} properties={'username': 'yourkpopsoul'}>
<User id=2132 labels={'User'} properties={'username': 'your_harrogate'}>
Enter fullscreen mode Exit fullscreen mode

We can also check the type of the retrieved records:

u = results[0]["u"]

print("User: ", u.username)
print("Type: ", type(u))
Enter fullscreen mode Exit fullscreen mode

Output:

User:  zziru67
Type:  <class '__main__.User'>
Enter fullscreen mode Exit fullscreen mode

Let's try to execute the same query with the GQLAlchemy query builder:

from gqlalchemy import match

results_from_qb = (
    match()
    .node(labels="User", variable="u")
    .return_()
    .order_by("u.username DESC")
    .limit(10)
    .execute()
)
results_from_qb = list(results_from_qb)

for result in results_from_qb:
    print(result["u"])
Enter fullscreen mode Exit fullscreen mode

Output:

<User id=3692 labels={'User'} properties={'username': 'zziru67'}>
<User id=3240 labels={'User'} properties={'username': 'zippydjh'}>
<User id=3725 labels={'User'} properties={'username': 'zee_row_ex'}>
<User id=3591 labels={'User'} properties={'username': 'yvonneqqm'}>
<User id=3212 labels={'User'} properties={'username': 'yujulia999'}>
<User id=2378 labels={'User'} properties={'username': 'yudhapati88'}>
<User id=2655 labels={'User'} properties={'username': 'yu100_kun'}>
<User id=2302 labels={'User'} properties={'username': 'youth_tree'}>
<User id=2432 labels={'User'} properties={'username': 'yourkpopsoul'}>
<User id=2132 labels={'User'} properties={'username': 'your_harrogate'}>
Enter fullscreen mode Exit fullscreen mode

9. Calculating PageRank

Now, let's do something clever with our graph. For example, calculating PageRank
for each node and then adding a rank property that stores the PageRank value
to each node:

results = memgraph.execute_and_fetch(
    """
    CALL pagerank.get()
    YIELD node, rank
    SET node.rank = rank
    RETURN node, rank
    ORDER BY rank DESC
    LIMIT 10;
    """
)

for result in results:
    print("The PageRank of node ", result["node"].username, ": ", result["rank"])
Enter fullscreen mode Exit fullscreen mode

Output:

The PageRank of node  WORLDMUSICAWARD :  0.13278838151391434
The PageRank of node  Kidzcoolit :  0.018924764871246207
The PageRank of node  HuobiGlobal :  0.011314994833838172
The PageRank of node  ChloeLe39602964 :  0.010011755296388128
The PageRank of node  getwhalinvest :  0.007228675936490175
The PageRank of node  Cooper_Lechat :  0.005577971882231625
The PageRank of node  Phemex_official :  0.005413803151353543
The PageRank of node  HamleysOfficial :  0.005325936307836382
The PageRank of node  bmstores :  0.00524546649693655
The PageRank of node  TheStourbridge :  0.004422198431576731
Enter fullscreen mode Exit fullscreen mode

Visit the Memgraph MAGE graph library (and
throw us a star ⭐) and take a look at all of the graph algorithms that have been
implemented. You can also implement and submit your own algorithms and utility
procedures.

10. Visualizing the graph in Memgraph Lab

Open Memgraph Lab in your browser on the address
localhost:3000. Execute the following Cypher query:

MATCH (n)-[r]-(m)
RETURN n, r, m
LIMIT 100;
Enter fullscreen mode Exit fullscreen mode

Now apply the following graph style to make your graph look more descriptive:

@NodeStyle {
  size: Sqrt(Mul(Div(Property(node, "rank"), 1), 200000))
  border-width: 1
  border-color: #000000
  shadow-color: #1D9BF0
  shadow-size: 10
  image-url: "https://i.imgur.com/UV7Nl0i.png"
}

@NodeStyle Greater(Size(Labels(node)), 0) {
  label: Format(":{}", Join(Labels(node), " :"))
}

@NodeStyle HasLabel(node, "User") {
  color: #1D9BF0
  color-hover: Darker(#dd2222)
  color-selected: #dd2222
}

@NodeStyle HasProperty(node, "username") {
  label: AsText(Property(node, "username"))
}

@EdgeStyle {
  width: 1
}
Enter fullscreen mode Exit fullscreen mode

memgraph-tutorial-twitter-dynamic-pagerank-visualization

Image 1. The radius of nodes is proportional to their PageRank value

What's next?

Now it's time for you to use Memgraph on a graph problem!

You can always check out Memgraph Playground
for some cool use cases and examples. If you have any questions, or want to
share your work with the rest of the community, join our Discord
Server.

Read more about Python and graph databases on memgraph.com

Top comments (0)

Read next

aishwarya_raj_978520e6399 profile image

Python Control Flow: If, Elif, Else, and Loops Without Going Loopy

Aishwarya Raj -

eziodeviox profile image

Building a Document Retrieval & Q&A System with OpenAI and Streamlit

EzioDeviox -

mantisus profile image

12 tips on how to think like a web scraping expert

Max Bohomolov -

codewithved profile image

FireDucks: Get performance beyond pandas with zero learning cost!

CodeWithVed -