[Data Mining] dataMIn

Description: Data Mining Retail Classification script
Platform: Python | Size: 1662KB | Author: Grimadso | Hits: 0

[Data Mining] mlcompare

Description: Data Mining spam classification comparison
Platform: Python | Size: 934KB | Author: Grimadso | Hits: 0

[Data Mining] SVM

Description: In the field of machine learning, support vector machine SVM (Support Vector Machine) is a supervised learning model, typically used for pattern recognition, classification, and regression analysis.
Platform: Python | Size: 9KB | Author: 黑色地位 | Hits: 0

[Data Mining] PCA

Description: Principal component analysis (Principal Component Analysis, PCA) or PCA. Is a statistical method to grasp the principal contradiction of things, it can be resolved diverse things out the main factors, revealing the essence of things, simplifying complex problems. The purpose of calculating the main component of high-dimensional data is projected to a lower dimensional space. Given n variables of m observations, forming an n ' m of the data matrix, n is usually large. For a complex matters described by several variables, it is difficult to know, so if you can grab something to focus on key aspects of analysis? If the main aspects of things just reflected on several key variables, we only need to separate out these few variables, for detailed analysis. However, in general, does not directly identify this critical variables. Then we can represent the major aspects of things with a linear combination of the original variables, PCA is one such analysis.
Platform: Python | Size: 3KB | Author: 黑色地位 | Hits: 0

[Data Mining] KNN

Description: Nearby algorithm, or K-nearest neighbor (kNN, k-NearestNeighbor) classification algorithm is one of classification data mining technology in the most simple way. The so-called K-nearest neighbor is the k nearest neighbors meant to say is that it can be used for each sample k nearest neighbors to represent. kNN algorithm core idea is that if a sample in feature space is k-nearest neighbor samples most belong to a category, the sample also fall into this category, and the category having the characteristics of the sample. The method in determining the classification decision based solely on the nearest one or several samples to determine the category to be sub-sample belongs to the category. kNN method when category decisions, with only a very small amount of adjacent samples related. Because kNN method is mainly limited by the surrounding adjacent samples, rather than the domain identification method to determine the class belongs to the category, so for class field of overlap or more s
Platform: Python | Size: 2KB | Author: 黑色地位 | Hits: 0

[Data Mining] DTW

Description: In isolated word speech recognition, the most simple and effective method is to use DTW (Dynamic Time Warping, Dynamic Time whole) algorithm based on dynamic programming (DP) of thinking to solve the problem of template matching pronunciation of varying lengths, is Earlier, more classic appearance of a speech recognition algorithm for isolated word recognition. In the training phase HMM algorithm needs to provide a large amount of speech data, by repeating the calculations to obtain the model parameters, and the algorithm of DTW training requires little extra computation. Therefore, in isolated word speech recognition, DTW algorithm is still widely used.
Platform: Python | Size: 2KB | Author: 黑色地位 | Hits: 1

[Data Mining] AdaBoost

Description: Adaboost is an iterative algorithm, the core idea is the same training set for training different classifiers (weak classifiers), then these weak classifiers together to form a stronger final classifier (strong classifier).
Platform: Python | Size: 3KB | Author: 黑色地位 | Hits: 0

[Data Mining] kmeans

Description: Mainly based on K-means clustering algorithm for converting color images to grayscale.
Platform: matlab | Size: 415KB | Author: fangella | Hits: 0

[Data Mining] FastICA_21

Description: FASTICA(mixedsig) estimates the independent components given multidimensional signals. Each row of matrix mixedsig is one observed signal. FASTICA uses Hyvarinen s fixed-point algorithm.
Platform: matlab | Size: 39KB | Author: w | Hits: 0

[Data Mining] kimag_fun

Description: image segmentation using k-means partitional clustering algorithm, matlab code
Platform: CHM | Size: 1KB | Author: pavan | Hits: 0

[Data Mining] rec

Description: Split movielens dataset to trainset and test set
Platform: Java | Size: 2KB | Author: 章旭 | Hits: 0

[Data Mining] reg

Description: Regex source collections, a positive sample expression and the basics of canonical
Platform: Java | Size: 11KB | Author: zheng hailong | Hits: 0