Python Tutorial Detecting a Brain Tumor with AI

Author(s): Ashutosh Malgaonkar

Originally published on Towards AI.

Brain Tumor

I. Bringing in the Data

II. Train-Test

III. Validation

IV. Metrics (Confusion Matrix, Sensitivity, Specificity)

I. Bringing in the Data

I used Google Colab as my editor. Using Python, type this in the notebook:

!pip install kaggle

Next, upload the kaggle.json file that you downloaded from Kaggle:

from google.colab import filesfiles.upload()

Once uploaded, run this:

!mkdir ~/.kaggle!cp kaggle.json ~/.kaggle/!chmod 600 ~/.kaggle/kaggle.json!kaggle datasets download -d jakeshbohaju/brain-tumor

Unzip the files:

!unzip brain-tumor.zip

Use Pandas to bring in the dataset:

# prompt: read Brain Tumor.csv into pandas dfimport pandas as pddf = pd.read_csv("/content/Brain Tumor.csv")

II. Train-Test

First, drop the Image column from the dataset because that is just a image number.

import pandas as pdfrom sklearn.model_selection import train_test_split# Assuming your DataFrame is called df# Drop the 'Image' columndf_without_image = df.drop(columns=['Image'])

Next, we know from our data that the class is in a column called class. In order to set it, we can set the class to Y and the rest of the features to X:

# Split the data into df_val (33%) and df (rest of the data)df,df_val = train_test_split(df_without_image, test_size=0.33, random_state=42)# Now you have df_val with 33% of the data and df with the rest of the data# Split the DataFrame df into features (X) and target (y)X = df.drop(columns=['Class']) # Featuresy = df['Class'] # Target# Split the data into… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI