I built a really cool Neural Network model with Tensorflow for cancer detection!

[vaipos]

With the help of Kaggle and my current certification, I put some extra time into building this project. It has an accuracy rate of 85.67% and I would like to opensource it with y'all!
`import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from sklearn.preprocessing import MinMaxScaler

data = pd.read_csv('sample_data/breast-cancer.csv')
data['diagnosis'] = data['diagnosis'].map({'B':1,'M':0})
x_train = data.drop('diagnosis', axis = 1)
y_train = data['diagnosis']

model = Sequential([
Dense(units = 31, activation= 'relu'),
Dense(units = 25, activation= 'relu'),
Dense(units = 20, activation= 'relu'),
Dense(units = 1, activation= 'sigmoid')
])
model.compile(
loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),
optimizer = tf.keras.optimizers.Adam(learning_rate=0.01),
)

model.fit(
x_train, y_train,
epochs=200,

)
accuracy = model.evaluate(x_train, y_train)
print(f'Accuracy: {accuracy * 100:.2f}%')`

[vaipos]

I hope this was something worth while!

[ylwu-amzn]

Thanks for sharing this! @vaipos , can you add more details like some document, test result etc.

[vaipos]

Yes sure! I am just getting familiar with some cool graphing techniques from Tensorboard and Keras's data viz tools, so I can provide you with an analytical graph sometime soon! But for now, here is the accuracy of this model and the dataset that was used!

breast-cancer.csv

[vaipos]

I have also built some Linear Regression and Logistics Regression models from SCRATCH (no scikit or tensorflow). This one has the dataset used, code, and graph based results!
Multiple_Variable.zip
Non-Linear.zip