Package com.leumanuel.woozydata.service
Class AdvancedAnalysisService
java.lang.Object
com.leumanuel.woozydata.service.AdvancedAnalysisService
Service class that provides advanced statistical analysis capabilities for DataFrames.
This class includes methods for time series analysis, outlier detection, missing value analysis,
and comprehensive statistical reporting.
-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionfullReport(DataFrame df, String... columns) Generates a comprehensive statistical report for specified columns.Analyzes missing values in all columns of the DataFrame.outlierAnalysis(DataFrame df, String... columns) Analyzes outliers in specified numeric columns using both Z-score and IQR methods.timeAnalysis(DataFrame df, String dateCol, String valueCol) Performs time series analysis on a DataFrame with date and value columns.
-
Constructor Details
-
AdvancedAnalysisService
public AdvancedAnalysisService()
-
-
Method Details
-
timeAnalysis
Performs time series analysis on a DataFrame with date and value columns.- Parameters:
df- The DataFrame containing the time series datadateCol- The name of the column containing date/time valuesvalueCol- The name of the column containing numeric values to analyze- Returns:
- DataFrame containing time series analysis results including trends, autocorrelation, and basic statistics
-
outlierAnalysis
Analyzes outliers in specified numeric columns using both Z-score and IQR methods.- Parameters:
df- The DataFrame to analyzecolumns- The column names to check for outliers- Returns:
- DataFrame containing outlier analysis results for each column including outlier counts, bounds, and detailed outlier information
-
missingAnalysis
Analyzes missing values in all columns of the DataFrame.- Parameters:
df- The DataFrame to analyze- Returns:
- DataFrame containing missing value analysis results including counts and percentages for each column
-
fullReport
Generates a comprehensive statistical report for specified columns.- Parameters:
df- The DataFrame to analyzecolumns- The columns to include in the report (if empty, all columns are analyzed)- Returns:
- Map containing detailed statistical analysis including basic statistics, missing values, outliers, correlations, and distribution analysis
-