.

logistic regression python code github

The optimization techniques work by defining a objective function and then find the parameters of the model that maximizes/minimizes the objective function. This notebook follows the topics discussed in logistic regression course notes. Loss function : 1.98470824149 Inputs to classification algorithm are real valued vectors of fixed dimensionality and outputs are the probability that input vector belongs to the specified class. "data = df[cols_to_keep].join(dummy_ranks.ix[:, 'prestige_2':])\n". Instead, we calculate values within the range of 30-100 as these are exam scores. The dimension of W is \(MxN\) while that of B is (Mx1).The output of the softmax function if a vector of dimension \(Mx1\). Logistic Regression is somehow similar to linear regression but it has different cost function and prediction function(hypothesis). It is one of those algorithms that everyone should be aware of. iteration : 1 We further get the models parameter for drawing the decision boundary. Using the logistic regression from SKlearn, we fit the same data and explore what the parameters are. "cols_to_keep = ['admit', 'gre', 'gpa']\n". View on GitHub Download .zip Download .tar.gz. The learning algorithm estimates the parameters of model .This is done using optimization technique by maximizing some objective function.The objective function in case of machine learning algorithms is called as a loss function. substituting x1=0 and find x2, then vice versa. number of classes : 10 All required libraries come inbuilt in anaconda suite. In this article we will look at a supervised machine learning algorithm called Logistic Regression Classifier for multi-class classification . Loss function : 0.811558448986 Here we get two features from iris dataset, and perform the logistic regression. Text classification is the automatic process of predicting one or more categories given a piece of text. 2 commits. Multinomial logistic regression is an extension of logistic regression that adds native support for multi-class classification problems. I am final year engineering grad who loves to explore technologies and currently dating every technology which i can find. Skip to content. number of dimensions : 784 If we use the same formula then our plot will look like this:-, So, in order to avoid this, we have smoothened the curve with the help of log and our cost function will look like this:-, where m=number of examples or rows in the dataset, x=feature values of i example, y=actual outcome of i example. In general any machine learning algorithm consists of a model,loss function,learning algorithm and optimizer. The back of the cheatsheet describes lubridates three timespan classes: periods, durations, and intervals; and explains how to do math with date-times. Firstly, we have defined the function read_filefor reading the dataset itself. You may need to install scikit machine learning package.The sklearn.metrics is used for accuracy metrics computation in validation methods of the LogsicticRegression class. x2= (-theta0 - theta1*100)/theta2, # plot function copied from https://scikit-learn.org/stable/auto_examples/linear_model/plot_iris_logistic.html, # plt.scatter(X[:, 0], X[:, 1], edgecolors='k', cmap=plt.cm.Paired), Python memory, ref counts, garbage collection, Geographical plotting with Basemap - matplotlib toolkit, Seaborn grids & custom - pair, facet grids, GeoPandas - GP, IO, interactive plotting, geocoding, Reading multi-dimensional data using open geo tools, PostGIS - SQLAlchemy, GeoAlchemy, GeoPandas, Implementing logistic regression in Python, Plot loss function for logistic regression. In this post, I built a logistic regression function from scratch and compared it with sk-learns logistic regression function. "gpas = np.linspace(data['gpa'].min(), data['gpa'].max(), 10)\n", "combos = DataFrame(cartesian([gres, gpas, [1, 2, 3, 4], [1.]]))". In algorithm function, we are calling the gradient_descent with epochs=1000 and learning_rate = 0.001. This cheatsheet covers how to round dates, work with time zones, extract elements of a date or time, parse dates into R and more. The data set consists of training,validation and test set. '/Users/atma6951/Documents/code/pychakras/pyChakras/ml/coursera-ml-matlabonline/machine-learning-ex/ex2'. GitHub - jpa203/Logistic-Regression. Logistic_Regression in Python This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. No. KNN is a distance based technique while Logistic regression is probability based. Though ppl say logistic regression is a classification type of algorithm, it is actually wrong to call Logistic regression a classification one. Classification should be ideally distinct, no areas of grey. Logistic regression takes the form of a logistic function with a sigmoid curve. These parameters are used to compute the class probability. The optimization function found in optimizer.py file corresponding to conjugate gradient descent algorithm is as below. tags: machine learning (logistic regression), python , jupyter notebook , imbalanced dataset metrics: Is for calculating the accuracies of the trained logistic regression model. 7d178ef 39 minutes ago. import numpy as np. import_basic_packages.py. jpa203 Create code.py. For the binary classification, we will get the probabilities to class 0 and to class 1. Thus, we write the equation as. Here, the file is opened with with so we dont have to close it and stored it in the reader variable. "png": "iVBORw0KGgoAAAANSUhEUgAAAXoAAAEICAYAAABRSj9aAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ncHiiZxiG6eHwRM8wDNPD+f+4IC6CwPLHdQAAAABJRU5ErkJggg==\n", "".

Religious Holiday Calendar 2023, 401 Prime Restaurant Lancaster, Pa, Best Roll Insulation For Attic, Ng-select Bindlabel Pipe, Ernakulam Junction Railway Station, Sims 3 Patch Notes Soundcloud, 16 Year-old Driving Restrictions Ny, Premier League Top Scorers 2023/24, Trufuel 50:1 Pre Mixed Fuel Plus Oil,

<

 

DKB-Cash: Das kostenlose Internet-Konto

 

 

 

 

 

 

 

 

OnVista Bank - Die neue Tradingfreiheit

 

 

 

 

 

 

Barclaycard Kredit für Selbständige