Spaces:

Zakia
/

DIARC

Runtime error

App Files Files Community

DIARC / src /diarc.py

Zakia

add a bunch of files and move .pkl file to models directory

712671d over 2 years ago

raw history blame contribute delete

No virus

4.12 kB

	# -- coding: utf-8 --
	"""diarc.ipynb

	Automatically generated by Colaboratory.

	Original file is located at
	https://colab.research.google.com/drive/1Jyccp5Aeml-7oZABbACY2VTE9iQJg9Pe

	# Bismillahir Rahmaanir Raheem
	# Almadadh Ya Gause RadiAllahu Ta'alah Anh - Ameen

	# <font color=grey>DIabetes-related Amputation Risk Calculator (DIARC)</font>
	<b>_by Zakia Salod_</b>
	"""

	!pip install pycaret

	from pycaret.utils import version
	version()

	from pycaret.utils import enable_colab
	enable_colab()

	import numpy as np # Linear algebra
	import pandas as pd # Data processing, CSV file I/O (e.g. pd.read_csv)
	import matplotlib.pyplot as plt # For graphical representations of the data
	import seaborn as sns

	# Just to make sure the results are reproducible
	np.random.seed(1234)

	dataset = pd.read_excel('amputation_dataset.xlsx')

	print(dataset['AMPUTATION'].value_counts())

	ax = sns.countplot(x="AMPUTATION", data=dataset)

	# show the number of duplicate rows in this dataset
	dataset.duplicated(keep='first').sum()

	# remove the duplicate rows in this dataset
	# only keep the first instance of the row
	dataset = dataset.drop_duplicates(keep='first')

	print(dataset['AMPUTATION'].value_counts())

	ax = sns.countplot(x="AMPUTATION", data=dataset)

	dataset.head()

	# Under sample the dataset to handle the imbalance
	# Shuffle the Dataset.
	shuffled_dataset = dataset.sample(frac=1, random_state=4)

	# Put all the amputation class in a separate dataset.
	amputation_dataset = shuffled_dataset.loc[shuffled_dataset['AMPUTATION'] == 1]


	#Randomly select 105 observations from the non-amputation (majority class)
	non_amputation_dataset = shuffled_dataset.loc[shuffled_dataset['AMPUTATION'] == 0].sample(n=105,random_state=42)

	# Concatenate both dataframes again
	dataset = pd.concat([amputation_dataset, non_amputation_dataset])

	print(dataset['AMPUTATION'].value_counts())

	ax = sns.countplot(x="AMPUTATION", data=dataset)

	dataset.to_excel('amputation_removed_duplicates_and_balanced.xlsx')

	from pycaret.classification import *

	clf = setup(data = dataset, target = 'AMPUTATION', session_id = 42)

	# display the dataset (X_train)
	get_config('X_train')
	# converts age from numeric to float
	# converts gender and diabetes_class (the two binary category variables) into label encoder conversion
	# so, gender_f ---> with value 1 indicating FEMALE is TRUE and value 0 indicating FEMALE is FALSE (and instead, MALE)
	# diabetes_class type 1 diabetes ---> value 1 indicates diabetes type 1 and value 0 means diabetes type 2
	# then, one hot encoding is applied to the race column (each race is split into separate columns, with value 1 denoting TRUE for that race)

	# display the dataset (y_train)
	get_config('y_train')

	best_model = compare_models(sort = 'AUC')

	# BLEND MODELS, ALHUM
	# create models for blending
	nb = create_model('nb')
	bagged_nb = ensemble_model(nb, method='Bagging')
	lr = create_model('lr')
	bagged_lr = ensemble_model(lr, method='Bagging')
	lda = create_model('lda')
	bagged_lda = ensemble_model(lda, method='Bagging')

	rf = create_model('rf')
	bagged_rf = ensemble_model(rf, method='Bagging')
	ada = create_model('ada')
	bagged_ada = ensemble_model(ada, method='Bagging')


	blend_specific = blend_models(estimator_list = [bagged_nb, bagged_lr, bagged_lda, bagged_rf, bagged_ada])

	# plot model
	plot_model(blend_specific)

	# tuning
	tuned_blend_specific = tune_model(blend_specific)

	evaluate_model(tuned_blend_specific)

	tuned_blend_specific_predictions = predict_model(tuned_blend_specific)

	# finalize model for deployment
	final_tuned_blend_specific = finalize_model(tuned_blend_specific)

	# save the model
	# creates a .pkl file
	save_model(tuned_blend_specific, "tuned_blend_specific_model_19112021", verbose=True)

	# display the dataset (X_test)
	get_config('X_test')

	# display the dataset (y_test)
	get_config('y_test')

	dataset2 = pd.read_excel('amputation_removed_duplicates_and_balanced.xlsx')

	!pip install pandas-profiling

	from pandas_profiling import ProfileReport

	profile = ProfileReport(dataset2, title="Pandas Profiling Report")

	profile.to_file("amputation_removed_duplicates_and_balanced_report.html")