diff --git a/va-server/visual-analytics/public/static/model-template/data/classification.json b/va-server/visual-analytics/public/static/model-template/data/classification.json index db7d6aff8..e2d65b2d4 100644 --- a/va-server/visual-analytics/public/static/model-template/data/classification.json +++ b/va-server/visual-analytics/public/static/model-template/data/classification.json @@ -4756,6 +4756,5 @@ "GAP_WIDTH": 55, "GAP_HEIGHT": 40 }, - "problemList": [], - "description": "
■ Dataset : US Census income dataset (modified from http://archive.ics.uci.edu/ml/datasets/Census+Income)
. y: >50K, <=50K.
. x: age, fnlwgt, education-num, gender, capital-gain, capital-loss, hours-per-week
■ Target: Develop the income prediction model.
■ Analytics process
. Exploratory Data Analysis : Identify the characteristics of the data
. Analysis: Divide the sample into train set and test set and preform KNN Classification and Random Forest Classification.
. Interpret results : Achieved accuracy 0.747 for KNN and 0.803 for Random Forest.
■ Dataset : Iris
. y: species
. x: sepal_length, sepal_width, petal_length, petal_width
■ Target: Clustering of individual iris by features
■ Analytics process
. Pre-Procession: One hot encoding for categorical variables (species)
. Exploratory Data Analysis : Identify the characteristics of the data
. Clustering : K-Means, Gaussian Mixture, Hierarchical clustering
. Apply results : Profiling for cluster, Labeling test data
■ Dataset: abalone dataset (retrieved from http://archive.ics.uci.edu/ml/datasets/Abalone)
. y: rings
. x: Sex, Length, Diameter, Height, Whole weight, Shucked weight, Viscera weight, Shell weight
■ Target: Develop model for the age of abalones
■ Analytics process
. Exploratory Data Analysis : Identify the characteristics of the data
. Analysis: Perform linear regression, XGB regression and penalized linear regreession+random forest regression and perform evaluation
. Interpret results : RMSE for linear regression is 2.200, XGB Regression is 2.187 and penalized+random forest is RMSE.
■ Dataset : Iris
. y: species
. x: sepal_length, sepal_width, petal_length, petal_width
■ Target: Preprocessing and Exploratory Data Analysis
■ Analytics process
. Exploratory Data Analysis : Identify the characteristics of the data
. Data preprocessing: Data preprocessing using Query Executor and Python Script
. Investigate summary statistics: Investigate distribution of data via summary statistics.
■ Dataset : US state of the union dataset
. variables: year, president, party, statement
■ Target: Perform sentiment analysis for the state of the union, and analyze it via linear regression
■ Analytics process
. Exploratory Data Analysis : Identify the characteristics of the data
. Preprocessing: Preprocess the text data
. Analysis: Doc2Vec, followed by SVM classification
. Interpret result: Doc2Vec vectors successfully predicted the party of the president
" + "problemList": [] } \ No newline at end of file