Devanshu Desai devanshuDesai

Data Engineer @ Meta

devanshuDesai / pipeline_dodgers.py

Created November 9, 2019 04:19

An example of a feature engineering + model pipeline I made

	from sklearn.compose import ColumnTransformer
	from sklearn.preprocessing import FunctionTransformer
	from sklearn.preprocessing import OneHotEncoder
	from sklearn.preprocessing import StandardScaler
	from sklearn.model_selection import train_test_split
	from sklearn.model_selection import GridSearchCV
	from sklearn.model_selection import StratifiedKFold
	from sklearn.pipeline import Pipeline
	from sklearn.decomposition import PCA
	from sklearn.linear_model import LogisticRegression

devanshuDesai / mnist_dodgers.py

Last active March 14, 2023 19:13

A neural network written in PyTorch with > 99% accuracy on the MNIST dataset.

	import torch
	from torch import nn
	from tqdm import tqdm_notebook

	class CNN(nn.Module):
	def __init__(self, input_size, num_classes):
	"""
	init convolution and activation layers
	Args:
	input_size: (1,28,28)