Keywords: features

Dcipher Analytics covers the following set of features. Click the visual feature tree to view it in full-size or explore the list of features below.

Features

NLP/Text analytics

  • Preprocessing
    └── Case modifications
    └── URL cleaning
    └── XML/HTML tag cleaning
    └── Tab/new line cleaning
    └── Hashtag cleaning
    └── Punctuation cleaning
    └── Spell checking
    └── Stop-word cleaning
    └── Substring/repeat cleaning
    └── Emoji cleaning
    └── Changing field types
    └── Changing date formats
    └── Automated text subtype detection

  • Text segmentation
    └── Split text into words
    └── Lemmatization
    └── Part-of-speech tagging
    └── Named Entity Recognition
    └── Phrase detection
    └── Split text into sentences
    └── Split text into paragraphs
    └── Rule-based paragraph boundary detection
    └── Context-aware paragraph boundary detection
    └── Content extraction
    └── Extract content based on keywords
    └── Extract content based on pattern

  • Vectorizers
    └── Word2Vec
    └── Doc2Vec
    └── FastText
    └── GloVe
    └── BERT
    └── ELMo
    └── OneHot Encoding

  • Enrichment
    └── Sentiment analysis
    └── Emojization & Emoji extraction
    └── Key phrase detection
    └── Language detection
    └── Concept detection
    └── Quotation detection
    └── Text statistics
    └── Date extraction
    └── Text summarization
    └── Topic detection

  • Semantic similarity modelling
    └── Document to document similarity calculations
    └── Document scoring based on words
    └── Word scoring based on words

  • Contextual analysis
    └── Cosine similarity on case-term frequency vectors
    └── CKC similarity on case-term frequency vectors
    └── Co-occurrence similarity
    └── Burst-based over-representation

  • Temporal analysis
    └── Momentum
    └── Burst detection
    └── Topic evolution analysis

  • Regular expression operations
    └── Split by pattern
    └── Extract properties by pattern
    └── Replace pattern

  • 3rd party integrations
    └── Google Translate
    └── Google NLP
    └── IBM Watson Natural Language Understanding

Machine learning

  • Supervised learning
    └── Classification
    └── Logistic Regression
    └── Decision Trees
    └── Random Forests
    └── Multilayer Neural Networks
    └── Support Vector Machines
    └── Naive Bayes
    └── Regression
    └── Linear Regression
    └── Decision Trees
    └── Random Forests
    └── Gradient Boosted Regressors
    └── Isotonic Regressors
    └── AFT Survival Regressors

  • Unsupervised learning
    └── Clustering
    └── K-means clustering
    └── Gaussian mixture clustering
    └── Power iteration clustering
    └── DBSCAN clustering
    └── Outlier scoring
    └── One-class SVM
    └── Robust Covarience
    └── Isolation Forest
    └── Local Outlier Factor
    └── Robust PCA
    └── Dimensionality reduction
    └── Principal component analysis
    └── Singular value decomposition
    └── T-distributed Stochastic Neighbor Embedding
    └── Uniform Manifold Approximation and Projection

  • Semi-supervised learning
    └── Classification
    └── Tagging
    └── Regression

Data visualization

  • Bar chart

  • Bubble cloud

  • Comparison cloud

  • Contour plot

  • Network

  • Heat map

  • Scatter plot

  • Schema

  • Table

  • Word cloud

Numerical operations

  • Preprocessing
    └── Formula-based transformations
    └── Discretization
    └── Normalization
    └── Imputation
    └── Convert numbers to words

  • Grouping and aggregations
    └── SQL aggregation functions
    └── Standard deviation
    └── Variance
    └── Median
    └── Vector sum
    └── Vector mean
    └── Entropy
    └── Gini-index​

Filtering

  • Numeric filters
    └── Greater than
    └── Greater than or equal to
    └── Smaller than
    └── Smaller than or equal to
    └── In between

  • Value filters
    └── Contains
    └── Does not contain
    └── Is one of
    └── Is not one of

  • Regexp filters
    └── Matches regexp
    └── Does not match regexp

  • Geometric filters
    └── Located inside
    └── Located outside

Import & export of data

  • Import data
    └── From file
    └── JSON file
    └── Delimiter-separated file (CSV, TSV, etc)
    └── PDF files(s)
    └── Excel file
    └── TXT file(s)
    └── From social media
    └── Facebook
    └── Twitter
    └── Instagram
    └── YouTube
    └── Forums
    └── Blogs

  • Export results
    └── As JSON
    └── As CSV/TSV
    └── As SVG

Did this answer your question?