add statiscial plot and better UI

Author: codechenx

README.md

@@ -30,6 +30,7 @@
 - [Features in Detail](#features-in-detail)
   - [Progressive Loading](#progressive-loading)
   - [Data Types and Sorting](#data-types-and-sorting)
+  - [Statistics and Visualization](#statistics-and-visualization)
   - [Search](#search)
   - [Column Filter](#column-filter)
   - [Text Wrapping](#text-wrapping)
@@ -48,7 +49,7 @@ tv brings spreadsheet-like functionality to your terminal with vim-inspired cont
 - **Column filtering** - Show only rows matching specific criteria
 - **Flexible sorting** - Sort by any column with intelligent type detection
 - **Text wrapping** - Wrap long cell content for better readability
-- **Statistics** - View column stats (min/max, mean for numbers; frequency for strings)
+- **Statistics & plots** - View column statistics with visual distribution charts
 - **Vim keybindings** - Navigate naturally with h/j/k/l and more
 - **Pipe support** - Read from stdin for seamless integration with shell pipelines
 
@@ -271,9 +272,25 @@ tv automatically detects column types and provides intelligent sorting.
 - **Numbers:** Numeric order (supports integers, floats, scientific notation, thousands separators)
 - **Dates:** Chronological order (supports ISO-8601, US format, EU format, and more)
 
-**View Statistics:** Press `i` to open a comprehensive statistics dialog showing:
-- **For numeric columns:** count, min, max, range, sum, mean, median, mode, standard deviation, variance, quartiles (Q1, Q2, Q3), and IQR
-- **For string columns:** total values, unique values, frequency distribution with percentages for each value
+### Statistics and Visualization
+
+Analyze your data with comprehensive statistics and modern ASCII plots.
+
+**View Statistics:** Press `i` on any column to open an interactive statistics dialog that displays:
+
+**For numeric columns:**
+- Summary stats: count, min, max, range, sum
+- Central tendency: mean, median, mode
+- Dispersion: standard deviation, variance
+- Quartiles: Q1, Q2, Q3, and IQR
+- **Visual distribution:** Histogram plot showing data distribution
+
+**For categorical/string columns:**
+- Total values, unique values, missing/empty count
+- Frequency distribution with percentages
+- **Visual distribution:** Bar chart of top 15 most frequent values
+
+The statistics dialog features a split-pane layout with numerical stats on the left and an ASCII graph visualization on the right, powered by `asciigraph` for modern, clean plots.
 
 ### Search
 
@@ -427,7 +444,7 @@ tv data.txt -s "  "
 - **Too many columns?** Use `--columns` to show only what you need
 - **Long text?** Press `W` to wrap the current column
 - **Wrong sort order?** Press `t` to change the column type, then `s` to re-sort
-- **Need stats?** Press `i` for comprehensive statistics including mean, median, quartiles, std dev, and frequency distributions
+- **Need insights?** Press `i` for comprehensive statistics with visual plots - histograms for numeric data, frequency charts for categorical data
 
 ## License
 

data/test/products-1000.csv

@@ -13,6 +13,7 @@ require (
 require (
 	github.com/clipperhouse/uax29/v2 v2.2.0 // indirect
 	github.com/gdamore/encoding v1.0.1 // indirect
+	github.com/guptarohit/asciigraph v0.7.3 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/lucasb-eyer/go-colorful v1.3.0 // indirect
 	github.com/mattn/go-colorable v0.1.14 // indirect

go.mod

@@ -7,6 +7,8 @@ github.com/gdamore/encoding v1.0.1 h1:YzKZckdBL6jVt2Gc+5p82qhrGiqMdG/eNs6Wy0u3Uh
 github.com/gdamore/encoding v1.0.1/go.mod h1:0Z0cMFinngz9kS1QfMjCP8TY7em3bZYeeklsSDPivEo=
 github.com/gdamore/tcell/v2 v2.9.0 h1:N6t+eqK7/xwtRPwxzs1PXeRWnm0H9l02CrgJ7DLn1ys=
 github.com/gdamore/tcell/v2 v2.9.0/go.mod h1:8/ZoqM9rxzYphT9tH/9LnunhV9oPBqwS8WHGYm5nrmo=
+github.com/guptarohit/asciigraph v0.7.3 h1:p05XDDn7cBTWiBqWb30mrwxd6oU0claAjqeytllnsPY=
+github.com/guptarohit/asciigraph v0.7.3/go.mod h1:dYl5wwK4gNsnFf9Zp+l06rFiDZ5YtXM6x7SRWZ3KGag=
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/lucasb-eyer/go-colorful v1.3.0 h1:2/yBRLdWBZKrf7gB40FoiKfAWYQ0lqNcbuQwVHXptag=

go.sum

@@ -3,13 +3,15 @@ package main
 import (
 	"sort"
 
+	"github.com/guptarohit/asciigraph"
 	"github.com/montanaflynn/stats"
 )
 
 type statsSummary interface {
 	summary(a []string)
 	getSummaryData() [][]string
 	getSummaryStr(a []string) string
+	getPlot() string
 }
 
 type DiscreteStats struct {
@@ -133,6 +135,51 @@ func (s *ContinuousStats) getSummaryStr(a []string) string {
 	return result
 }
 
+// getPlot generates a histogram visualization for continuous data
+func (s *ContinuousStats) getPlot() string {
+	if len(s.data) == 0 {
+		return "No data to plot"
+	}
+
+	// Create histogram bins
+	numBins := 20
+	if len(s.data) < 100 {
+		numBins = 10
+	}
+	if len(s.data) < 20 {
+		numBins = 5
+	}
+
+	// Calculate bin width
+	binWidth := (s.max - s.min) / float64(numBins)
+	if binWidth == 0 {
+		return "All values are identical"
+	}
+
+	// Initialize bins
+	bins := make([]float64, numBins)
+	
+	// Count values in each bin
+	for _, v := range s.data {
+		binIndex := int((v - s.min) / binWidth)
+		if binIndex >= numBins {
+			binIndex = numBins - 1
+		}
+		if binIndex < 0 {
+			binIndex = 0
+		}
+		bins[binIndex]++
+	}
+
+	// Generate the plot
+	plot := asciigraph.Plot(bins,
+		asciigraph.Height(15),
+		asciigraph.Width(60),
+		asciigraph.Caption("Distribution Histogram"))
+
+	return plot
+}
+
 func (s *DiscreteStats) summary(a []string) {
 	s.data = a
 	s.count = len(a)
@@ -235,3 +282,43 @@ func (s *DiscreteStats) getSummaryStr(a []string) string {
 
 	return result
 }
+
+// getPlot generates a bar chart visualization for discrete data
+func (s *DiscreteStats) getPlot() string {
+	if len(s.counter) == 0 {
+		return "No data to plot"
+	}
+
+	// Sort by frequency
+	type kv struct {
+		Key   string
+		Value int
+	}
+	var ss []kv
+	for k, v := range s.counter {
+		ss = append(ss, kv{k, v})
+	}
+	sort.Slice(ss, func(i, j int) bool {
+		return ss[i].Value > ss[j].Value
+	})
+
+	// Take top 15 values for the plot
+	maxDisplay := 15
+	if len(ss) < maxDisplay {
+		maxDisplay = len(ss)
+	}
+
+	// Prepare data for plotting
+	frequencies := make([]float64, maxDisplay)
+	for i := 0; i < maxDisplay; i++ {
+		frequencies[i] = float64(ss[i].Value)
+	}
+
+	// Generate the plot
+	plot := asciigraph.Plot(frequencies,
+		asciigraph.Height(12),
+		asciigraph.Width(60),
+		asciigraph.Caption("Top Values Frequency"))
+
+	return plot
+}

install.sh

@@ -162,3 +162,75 @@ func BenchmarkDiscreteStats(b *testing.B) {
 		ds.summary(data)
 	}
 }
+
+// ========================================
+// Plot Tests
+// ========================================
+
+func TestContinuousStats_GetPlot(t *testing.T) {
+	cs := &ContinuousStats{}
+	data := []string{"10", "20", "15", "25", "30", "18", "22", "27", "12", "16"}
+
+	cs.summary(data)
+	plot := cs.getPlot()
+
+	if len(plot) == 0 {
+		t.Error("Expected plot output, got empty string")
+	}
+	if plot == "No data to plot" {
+		t.Error("Should generate plot for valid data")
+	}
+	t.Logf("Plot output:\n%s", plot)
+}
+
+func TestContinuousStats_GetPlot_EmptyData(t *testing.T) {
+	cs := &ContinuousStats{}
+	data := []string{}
+
+	cs.summary(data)
+	plot := cs.getPlot()
+
+	if plot != "No data to plot" {
+		t.Errorf("Expected 'No data to plot', got: %s", plot)
+	}
+}
+
+func TestContinuousStats_GetPlot_IdenticalValues(t *testing.T) {
+	cs := &ContinuousStats{}
+	data := []string{"42", "42", "42", "42", "42"}
+
+	cs.summary(data)
+	plot := cs.getPlot()
+
+	if plot != "All values are identical" {
+		t.Errorf("Expected 'All values are identical', got: %s", plot)
+	}
+}
+
+func TestDiscreteStats_GetPlot(t *testing.T) {
+	ds := &DiscreteStats{}
+	data := []string{"A", "B", "A", "C", "A", "B", "A", "D", "A", "B"}
+
+	ds.summary(data)
+	plot := ds.getPlot()
+
+	if len(plot) == 0 {
+		t.Error("Expected plot output, got empty string")
+	}
+	if plot == "No data to plot" {
+		t.Error("Should generate plot for valid data")
+	}
+	t.Logf("Plot output:\n%s", plot)
+}
+
+func TestDiscreteStats_GetPlot_EmptyData(t *testing.T) {
+	ds := &DiscreteStats{}
+	data := []string{}
+
+	ds.summary(data)
+	plot := ds.getPlot()
+
+	if plot != "No data to plot" {
+		t.Errorf("Expected 'No data to plot', got: %s", plot)
+	}
+}