{"id":29016461,"url":"https://github.com/prudhvignv/py-automl","last_synced_at":"2026-02-27T19:47:35.119Z","repository":{"id":62578806,"uuid":"287723651","full_name":"PrudhviGNV/py-automl","owner":"PrudhviGNV","description":"A low code machine learning python library. ","archived":false,"fork":false,"pushed_at":"2022-09-30T06:35:47.000Z","size":440,"stargazers_count":5,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-24T22:50:35.536Z","etag":null,"topics":["deep-learning","keras","machine-learning","pip","py-automl","pypi-package","python","scikit-learn"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/py-automl/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PrudhviGNV.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-08-15T10:18:28.000Z","updated_at":"2024-06-19T15:34:47.000Z","dependencies_parsed_at":"2022-11-03T21:00:31.612Z","dependency_job_id":null,"html_url":"https://github.com/PrudhviGNV/py-automl","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/PrudhviGNV/py-automl","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrudhviGNV%2Fpy-automl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrudhviGNV%2Fpy-automl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrudhviGNV%2Fpy-automl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrudhviGNV%2Fpy-automl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PrudhviGNV","download_url":"https://codeload.github.com/PrudhviGNV/py-automl/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PrudhviGNV%2Fpy-automl/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261962037,"owners_count":23236856,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","keras","machine-learning","pip","py-automl","pypi-package","python","scikit-learn"],"created_at":"2025-06-25T22:30:17.973Z","updated_at":"2026-02-27T19:47:35.088Z","avatar_url":"https://github.com/PrudhviGNV.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Py-AutoML\r\n\r\n\r\n[![LICENCE.md](https://img.shields.io/github/license/PrudhviGNV/py-automl)](https://github.com/PrudhviGNV/py-automl/blob/master/LICENCE.md)\r\n[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://GitHub.com/PrudhviGNV/py-automl)\r\n[![Website prudhvignv.github.io](https://img.shields.io/website-up-down-green-red/https/naereen.github.io.svg)](https://prudhvignv.github.io/)\r\n[![Ask Me Anything !](https://img.shields.io/badge/Ask%20me-anything-1abc9c.svg)](https://GitHub.com/PrudhviGNV)\r\n \r\n  \r\n[![PyPI version fury.io](https://badge.fury.io/py/py-automl.svg)](https://pypi.python.org/pypi/py-automl/)\r\n[![PyPI format](https://img.shields.io/pypi/format/ansicolortags.svg)](https://pypi.python.org/pypi/py-automl/)\r\n[![PyPI pyversions](https://img.shields.io/pypi/pyversions/py-automl.svg)](https://pypi.python.org/pypi/py-automl/)\r\n[![PyPI status](https://img.shields.io/pypi/status/py-automl.svg)](https://pypi.python.org/pypi/py-automl/) \r\n[![Open Source Love svg2](https://badges.frapsoft.com/os/v2/open-source.svg?v=103)](https://github.com/PrudhviGNV/open-source-badges/)\r\n[![Awesome Badges](https://img.shields.io/badge/badges-awesome-green.svg)](https://github.com/PrudhviGNV/badges)\r\n\r\n\r\n\r\n\r\n\r\n\r\n\r\n  \r\n\r\n\r\n\r\n# Introduction\r\n\r\n## What is Py-AutoML?\r\nPy-AutoML is an open source `low-code` machine learning library in Python that aims to reduce the hypothesis to insights cycle time in a ML experiment. It mainly helps to do our pet projects quickly and efficiently. In comparison with the other open source machine learning libraries, Py-AutoML is an alternative low-code library that can be used to perform complex machine learning tasks with only few lines of code. Py-AutoML is essentially a Python wrapper around several machine learning libraries and frameworks such as `scikit-learn`, 'tensorflow','keras' and many more. \r\n\r\nThe design and simplicity of Py-AutoML is inspired by the  two principles KISS (keep it simple and sweet) and DRY (Don't Repeat Yourself) . We as engineers have to find a way  effective way to mitigate this gap and address data related challenges in business setting.\r\n\r\n\r\n# Modules\r\nPy-AutoML is a minimalistic library which not  simplifies the machine learning tasks and also makes our work easier.\r\n\r\nPy-AutoML consists of so many functionalities. such as \r\n-----------------\r\n\r\n   - #### model.py- implementing popular neural networks such as googlenet , vgg16, simple cnn ,basic cnn, lenet5, alexnet, lstm, mlp etc..\r\n   - #### checkpoint.py - consists of callbacks function which is used to store metrics \r\n   - #### utils.py - consists of some functionalities used to preprocess test images, spliting the data.\r\n   - #### preprocess.py - used to preprocess image dataset such as resize, reshape, convert to greyscale, normalisation etc..\r\n   - #### ml.py - allow us to implement and check metrics of popular classical machine learning models such as random forest, decision tree, svm , logistic regression and also displays metric reports of every model\r\n   - #### visualize.py - allow us to visualize neural networks in pictorial and graphs form.\r\n   \r\n   \r\n # ml.py -\u003e Implemented algorithms\r\n\r\n------------\r\n- ### Logistic Regression\r\n- ### Support Vector Machine\r\n- ### Decision Tree Classifier\r\n- ### Random Forest Classifier\r\n- ### K-Nearest Neighbors\r\n--------------------------\r\n\r\n   \r\n # model.py -\u003e Implemented popular neural network architectures\r\n\r\n------------\r\n- ### GoogleNet\r\n- ### VGG16\r\n- ### AlexNet\r\n- ### Lenet5\r\n- ### Inception\r\n- ### simple \u0026 basic cnn\r\n- ### basic_mlp \u0026 deep_mlp\r\n- ### lstm\r\nwith predefined configurations\r\n--------------------------\r\n# Getting started\r\n\r\n-----------------\r\n\r\n## Install the package\r\n```bash\r\npip install py-automl\r\n```\r\nNavigate to folder and install requirements: \r\n```bash\r\npip install -r requirements.txt\r\n\r\n```\r\n\r\n## Usage\r\nImporting the package\r\n```python\r\nimport pyAutoML\r\nfrom pyAutoML import *\r\nfrom pyAutoML.model import *\r\n# like that...\r\n```\r\nAssign the variables X and Y to the desired columns and assign the variable size to the desired test_size.  \r\n```python\r\nX = \u003c df.features \u003e\r\nY = \u003c df.target \u003e\r\nsize = \u003c test_size \u003e\r\n```\r\n## Encoding Categorical Data \r\nEncode target variable if non-numerical:\r\n```python\r\nfrom pyAutoML import *\r\nY = EncodeCategorical(Y)\r\n```\r\n## Running py-automl\r\n\r\nsignature is as follows :   ML(X, Y, size=0.25, *args)\r\n```python\r\nfrom pyAutoML.ml import ML,ml, EncodeCategorical\r\n\r\nimport pandas as pd\r\nimport numpy as np\r\nfrom sklearn.ensemble import RandomForestClassifier\r\nfrom sklearn.tree import DecisionTreeClassifier\r\nfrom sklearn.neighbors import KNeighborsClassifier\r\nfrom sklearn.linear_model import LogisticRegression\r\nfrom sklearn.svm import SVC\r\nfrom sklearn import datasets\r\n\r\n\r\n\r\n\r\n##reading the Iris dataset into the code\r\ndf =  datasets.load_iris()\r\n\r\n##assigning the desired columns to X and Y  in preparation for running fastML\r\nX = df.data[:, :4]\r\nY = df.target\r\n\r\n##running the EncodeCategorical function from fastML to handle the process of categorial encoding of data\r\nY = EncodeCategorical(Y)\r\nsize = 0.33\r\n\r\nML(X, Y, size, SVC(), RandomForestClassifier(), DecisionTreeClassifier(), KNeighborsClassifier(), LogisticRegression(max_iter = 7000))\r\n\r\n```\r\n### output\r\n```python\r\n____________________________________________________\r\n.....................Py-AutoML......................\r\n____________________________________________________\r\nSVC ______________________________ \r\n\r\nAccuracy Score for SVC is \r\n0.98\r\n\r\n\r\nConfusion Matrix for SVC is \r\n[[16  0  0]\r\n [ 0 18  1]\r\n [ 0  0 15]]\r\n\r\n\r\nClassification Report for SVC is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        16\r\n           1       1.00      0.95      0.97        19\r\n           2       0.94      1.00      0.97        15\r\n\r\n    accuracy                           0.98        50\r\n   macro avg       0.98      0.98      0.98        50\r\nweighted avg       0.98      0.98      0.98        50\r\n\r\n\r\n\r\n____________________________________________________\r\nRandomForestClassifier ______________________________ \r\n\r\nAccuracy Score for RandomForestClassifier is \r\n0.96\r\n\r\n\r\nConfusion Matrix for RandomForestClassifier is \r\n[[16  0  0]\r\n [ 0 18  1]\r\n [ 0  1 14]]\r\n\r\n\r\nClassification Report for RandomForestClassifier is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        16\r\n           1       0.95      0.95      0.95        19\r\n           2       0.93      0.93      0.93        15\r\n\r\n    accuracy                           0.96        50\r\n   macro avg       0.96      0.96      0.96        50\r\nweighted avg       0.96      0.96      0.96        50\r\n\r\n\r\n\r\n____________________________________________________\r\nDecisionTreeClassifier ______________________________ \r\n\r\nAccuracy Score for DecisionTreeClassifier is \r\n0.98\r\n\r\n\r\nConfusion Matrix for DecisionTreeClassifier is \r\n[[16  0  0]\r\n [ 0 18  1]\r\n [ 0  0 15]]\r\n\r\n\r\nClassification Report for DecisionTreeClassifier is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        16\r\n           1       1.00      0.95      0.97        19\r\n           2       0.94      1.00      0.97        15\r\n\r\n    accuracy                           0.98        50\r\n   macro avg       0.98      0.98      0.98        50\r\nweighted avg       0.98      0.98      0.98        50\r\n\r\n\r\n\r\n____________________________________________________\r\nKNeighborsClassifier ______________________________ \r\n\r\nAccuracy Score for KNeighborsClassifier is \r\n0.98\r\n\r\n\r\nConfusion Matrix for KNeighborsClassifier is \r\n[[16  0  0]\r\n [ 0 18  1]\r\n [ 0  0 15]]\r\n\r\n\r\nClassification Report for KNeighborsClassifier is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        16\r\n           1       1.00      0.95      0.97        19\r\n           2       0.94      1.00      0.97        15\r\n\r\n    accuracy                           0.98        50\r\n   macro avg       0.98      0.98      0.98        50\r\nweighted avg       0.98      0.98      0.98        50\r\n\r\n\r\n\r\n____________________________________________________\r\nLogisticRegression ______________________________ \r\n\r\nAccuracy Score for LogisticRegression is \r\n0.98\r\n\r\n\r\nConfusion Matrix for LogisticRegression is \r\n[[16  0  0]\r\n [ 0 18  1]\r\n [ 0  0 15]]\r\n\r\n\r\nClassification Report for LogisticRegression is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        16\r\n           1       1.00      0.95      0.97        19\r\n           2       0.94      1.00      0.97        15\r\n\r\n    accuracy                           0.98        50\r\n   macro avg       0.98      0.98      0.98        50\r\nweighted avg       0.98      0.98      0.98        50\r\n\r\n\r\n\r\n                    Model Accuracy\r\n0                     SVC     0.98\r\n1  RandomForestClassifier     0.96\r\n2  DecisionTreeClassifier     0.98\r\n3    KNeighborsClassifier     0.98\r\n4      LogisticRegression     0.98\r\n```\r\n\r\n### you can also write as follows\r\n```python\r\nML(X,Y)\r\n```\r\n### output\r\n```python\r\n____________________________________________________\r\n.....................Py-AutoML......................\r\n____________________________________________________\r\nSVC ______________________________ \r\n\r\nAccuracy Score for SVC is \r\n0.9736842105263158\r\n\r\n\r\nConfusion Matrix for SVC is \r\n[[13  0  0]\r\n [ 0 15  1]\r\n [ 0  0  9]]\r\n\r\n\r\nClassification Report for SVC is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        13\r\n           1       1.00      0.94      0.97        16\r\n           2       0.90      1.00      0.95         9\r\n\r\n    accuracy                           0.97        38\r\n   macro avg       0.97      0.98      0.97        38\r\nweighted avg       0.98      0.97      0.97        38\r\n\r\n\r\n\r\n____________________________________________________\r\nRandomForestClassifier ______________________________ \r\n\r\nAccuracy Score for RandomForestClassifier is \r\n0.9736842105263158\r\n\r\n\r\nConfusion Matrix for RandomForestClassifier is \r\n[[13  0  0]\r\n [ 0 15  1]\r\n [ 0  0  9]]\r\n\r\n\r\nClassification Report for RandomForestClassifier is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        13\r\n           1       1.00      0.94      0.97        16\r\n           2       0.90      1.00      0.95         9\r\n\r\n    accuracy                           0.97        38\r\n   macro avg       0.97      0.98      0.97        38\r\nweighted avg       0.98      0.97      0.97        38\r\n\r\n\r\n\r\n____________________________________________________\r\nDecisionTreeClassifier ______________________________ \r\n\r\nAccuracy Score for DecisionTreeClassifier is \r\n0.9736842105263158\r\n\r\n\r\nConfusion Matrix for DecisionTreeClassifier is \r\n[[13  0  0]\r\n [ 0 15  1]\r\n [ 0  0  9]]\r\n\r\n\r\nClassification Report for DecisionTreeClassifier is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        13\r\n           1       1.00      0.94      0.97        16\r\n           2       0.90      1.00      0.95         9\r\n\r\n    accuracy                           0.97        38\r\n   macro avg       0.97      0.98      0.97        38\r\nweighted avg       0.98      0.97      0.97        38\r\n\r\n\r\n____________________________________________________\r\nKNeighborsClassifier ______________________________ \r\n\r\nAccuracy Score for KNeighborsClassifier is \r\n0.9736842105263158\r\n\r\n\r\nConfusion Matrix for KNeighborsClassifier is \r\n[[13  0  0]\r\n [ 0 15  1]\r\n [ 0  0  9]]\r\n\r\n\r\nClassification Report for KNeighborsClassifier is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        13\r\n           1       1.00      0.94      0.97        16\r\n           2       0.90      1.00      0.95         9\r\n\r\n    accuracy                           0.97        38\r\n   macro avg       0.97      0.98      0.97        38\r\nweighted avg       0.98      0.97      0.97        38\r\n\r\n\r\n\r\n____________________________________________________\r\nLogisticRegression ______________________________ \r\n\r\nAccuracy Score for LogisticRegression is \r\n0.9736842105263158\r\n\r\n\r\nConfusion Matrix for LogisticRegression is \r\n[[13  0  0]\r\n [ 0 15  1]\r\n [ 0  0  9]]\r\n\r\n\r\nClassification Report for LogisticRegression is \r\n              precision    recall  f1-score   support\r\n\r\n           0       1.00      1.00      1.00        13\r\n           1       1.00      0.94      0.97        16\r\n           2       0.90      1.00      0.95         9\r\n\r\n    accuracy                           0.97        38\r\n   macro avg       0.97      0.98      0.97        38\r\nweighted avg       0.98      0.97      0.97        38\r\n\r\n\r\n\r\n                    Model            Accuracy\r\n0                     SVC  0.9736842105263158\r\n1  RandomForestClassifier  0.9736842105263158\r\n2  DecisionTreeClassifier  0.9736842105263158\r\n3    KNeighborsClassifier  0.9736842105263158\r\n4      LogisticRegression  0.9736842105263158\r\n```\r\n\r\n   \r\n ## Defining popular neural networks\r\n \r\n ### implementing alexNet may looks like this\r\n \r\n ```python\r\n  #Instantiation\r\n    AlexNet = Sequential()\r\n\r\n    #1st Convolutional Layer\r\n    AlexNet.add(Conv2D(filters=96, input_shape=input_shape, kernel_size=(11,11), strides=(4,4), padding='same'))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n    AlexNet.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'))\r\n\r\n    #2nd Convolutional Layer\r\n    AlexNet.add(Conv2D(filters=256, kernel_size=(5, 5), strides=(1,1), padding='same'))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n    AlexNet.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'))\r\n\r\n    #3rd Convolutional Layer\r\n    AlexNet.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding='same'))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n\r\n    #4th Convolutional Layer\r\n    AlexNet.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding='same'))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n\r\n    #5th Convolutional Layer\r\n    AlexNet.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), padding='same'))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n    AlexNet.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'))\r\n\r\n    #Passing it to a Fully Connected layer\r\n    AlexNet.add(Flatten())\r\n    # 1st Fully Connected Layer\r\n    AlexNet.add(Dense(4096, input_shape=(32,32,3,)))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n    # Add Dropout to prevent overfitting\r\n    AlexNet.add(Dropout(0.4))\r\n\r\n    #2nd Fully Connected Layer\r\n    AlexNet.add(Dense(4096))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n    #Add Dropout\r\n    AlexNet.add(Dropout(0.4))\r\n\r\n    #3rd Fully Connected Layer\r\n    AlexNet.add(Dense(1000))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation('relu'))\r\n    #Add Dropout\r\n    AlexNet.add(Dropout(0.4))\r\n\r\n    #Output Layer\r\n    AlexNet.add(Dense(10))\r\n    AlexNet.add(BatchNormalization())\r\n    AlexNet.add(Activation(classifier_function))\r\n\r\n    AlexNet.compile('adam', loss_function, metrics=['acc'])\r\n    return AlexNet\r\n```\r\nBut we implement this in a single line of code like below using this package.\r\n```python\r\nalexNet_model = model(input_shape= (30,30,4) , arch=\"alexNet\", classify=\"Mulit\" )\r\n```\r\nSimilarly we can also implement\r\n```python\r\nalexNet_model = model(\"alexNet\")\r\n\r\nlenet5_model = model(\"lenet5\")\r\n\r\ngoogleNet_model = model(\"googleNet\")\r\n\r\nvgg16_model = model(\"vgg16\")\r\n\r\n### etc...\r\n\r\n```\r\nFor more generalization , let's observe following code.\r\n```python\r\n# Lets take all models that are defined in the py_automl and which are implemented in a signle line of code\r\nmodels = [\"simple_cnn\", \"basic_cnn\", \"googleNet\", \"inception\",\"vgg16\",\"lenet5\",\"alexNet\", \"basic_mlp\",\"deep_mlp\",\"basic_lstm\",\"deep_lstm\" ]\r\n\r\nd= {}\r\n\r\nfor i in models:\r\n  d[i] = model(i)  # assigning all architectures to its model names using dictionary\r\n  \r\n```\r\n\r\n## Visualization \r\n### we can visualize neural networks architecture in different forms with ease.\r\nLet's observe the following code for better understanding\r\n```python\r\nimport keras\r\nfrom keras import layers\r\nmodel = keras.Sequential()\r\n\r\nmodel.add(layers.Conv2D(filters=6, kernel_size=(3, 3), activation='relu', input_shape=(32,32,1)))\r\nmodel.add(layers.AveragePooling2D())\r\n\r\nmodel.add(layers.Conv2D(filters=16, kernel_size=(3, 3), activation='relu'))\r\nmodel.add(layers.AveragePooling2D())\r\n\r\nmodel.add(layers.Flatten())\r\n\r\nmodel.add(layers.Dense(units=120, activation='relu'))\r\n\r\nmodel.add(layers.Dense(units=84, activation='relu'))\r\n\r\nmodel.add(layers.Dense(units=10, activation = 'softmax'))\r\n```\r\nnow let's visualise this\r\n```python \r\nnn_visualize(model)\r\n```\r\nBy default , it returns keras visualization object\r\n### output:\r\n![i1](https://user-images.githubusercontent.com/39909903/91040097-840bbf80-e5c2-11ea-8c3d-fad294b20722.png)\r\n\r\n\r\n```python\r\n\r\nfrom keras.models import Sequential\r\nfrom keras.layers import Dense\r\nimport numpy\r\n# fix random seed for reproducibility\r\nnumpy.random.seed(7)\r\n# load pima indians dataset\r\ndataset = numpy.loadtxt(\"pima-indians-diabetes.csv\", delimiter=\",\")\r\n# split into input (X) and output (Y) variables\r\nX = dataset[:,0:8]\r\nY = dataset[:,8]\r\n# create model\r\nmodel = Sequential()\r\nmodel.add(Dense(12, input_dim=8, activation='relu'))\r\nmodel.add(Dense(8, activation='relu'))\r\nmodel.add(Dense(1, activation='sigmoid'))\r\n# Compile model\r\nmodel.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])\r\n# Fit the model\r\nmodel.fit(X, Y, epochs=150, batch_size=10)\r\n# evaluate the model\r\nscores = model.evaluate(X, Y)\r\nprint(\"\\n%s: %.2f%%\" % (model.metrics_names[1], scores[1]*100))\r\n\r\n\r\n\r\n#Neural network visualization \r\n\r\nnn_visualize(model,type = \"graphviz\")\r\n\r\n```\r\n### output\r\n![1_gTwmrLh1aYLzayMylHGIeg](https://user-images.githubusercontent.com/39909903/91041224-8242fb80-e5c4-11ea-8539-4c2c35f7bab5.jpeg)\r\n\r\n\r\nThis library is so developer friendly that even we declare type with starting letters.\r\n```python\r\nfrom pyAutoML.model import *\r\nmodel2 = model(arch=\"alexNet\")\r\n\r\nnn_visualize(model2,type=\"k\")\r\n\r\n```\r\n### output:\r\n![i3](https://user-images.githubusercontent.com/39909903/91040108-8837dd00-e5c2-11ea-87c4-a9951804d3c8.png)\r\n\r\n## This is a minimal documentation about the package. \u003cbr/\u003e\r\nFor more information and understanding, see examples [HERE](https://github.com/PrudhviGNV/py-automl/edit/master/examples)\r\nand source code: [GITHUB](https://github.com/PrudhviGNV/py-automl)\r\n-------\r\n\r\n## Author: [Prudhvi GNV](prudhvignv.github.io)\r\n-------\r\n# Contact:\r\n\r\n[LinkedIn](https://linkedin.com/in/prudhvignv/) \u003cbr/\u003e\r\n[Github](https://github.com/PrudhviGNV) \u003cbr/\u003e\r\n[Instagram](https://instagram.com/prudhvi-gnv)\r\n\r\n\r\n\r\n\r\n \r\n\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprudhvignv%2Fpy-automl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprudhvignv%2Fpy-automl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprudhvignv%2Fpy-automl/lists"}