greeners 2.0.1

High-performance econometrics with R/Python formulas
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182

use greeners_core::dataframe::DataFrame;

fn main() {
    println!("=== PIVOT TABLES - Reshape Data ===\n");

    // ========== PIVOT TABLE (Long to Wide) ==========
    println!("=== PIVOT TABLE - Long to Wide Format ===\n");

    // Sales data in LONG format (typical database format)
    let sales_long = DataFrame::builder()
        .add_column("date", vec![1.0, 1.0, 1.0, 2.0, 2.0, 2.0, 3.0, 3.0, 3.0])
        .add_column("product", vec![1.0, 2.0, 3.0, 1.0, 2.0, 3.0, 1.0, 2.0, 3.0])
        .add_column("region", vec![1.0, 1.0, 1.0, 2.0, 2.0, 2.0, 1.0, 1.0, 1.0])
        .add_column(
            "sales",
            vec![
                100.0, 150.0, 200.0, 120.0, 180.0, 220.0, 110.0, 160.0, 210.0,
            ],
        )
        .build()
        .unwrap();

    println!("Original data (LONG format):");
    println!("{}\n", sales_long);

    // Pivot: Products as rows, Regions as columns
    println!("--- Pivot: Products (rows) × Regions (columns) ---");
    let pivot1 = sales_long
        .pivot_table("product", "region", "sales", "sum")
        .unwrap();
    println!("Total sales by product and region:");
    println!("{}\n", pivot1);

    // Pivot: Dates as rows, Products as columns
    println!("--- Pivot: Dates (rows) × Products (columns) ---");
    let pivot2 = sales_long
        .pivot_table("date", "product", "sales", "sum")
        .unwrap();
    println!("Total sales by date and product:");
    println!("{}\n", pivot2);

    // Different aggregations
    println!("--- Pivot with MEAN aggregation ---");
    let pivot_mean = sales_long
        .pivot_table("product", "region", "sales", "mean")
        .unwrap();
    println!("Average sales by product and region:");
    println!("{}\n", pivot_mean);

    println!("--- Pivot with COUNT aggregation ---");
    let pivot_count = sales_long
        .pivot_table("product", "region", "sales", "count")
        .unwrap();
    println!("Number of transactions by product and region:");
    println!("{}\n", pivot_count);

    println!("--- Pivot with MAX aggregation ---");
    let pivot_max = sales_long
        .pivot_table("date", "product", "sales", "max")
        .unwrap();
    println!("Maximum sales by date and product:");
    println!("{}\n", pivot_max);

    // ========== MELT (Wide to Long) ==========
    println!("\n=== MELT - Wide to Long Format ===\n");

    // Monthly revenue in WIDE format (spreadsheet style)
    let revenue_wide = DataFrame::builder()
        .add_column("product", vec![1.0, 2.0, 3.0])
        .add_column("Jan", vec![100.0, 150.0, 200.0])
        .add_column("Feb", vec![120.0, 160.0, 210.0])
        .add_column("Mar", vec![110.0, 170.0, 220.0])
        .build()
        .unwrap();

    println!("Original data (WIDE format - spreadsheet style):");
    println!("{}\n", revenue_wide);

    // Melt to long format
    println!("--- After MELT (long format) ---");
    let revenue_long = revenue_wide
        .melt(&["product"], None, "month", "revenue")
        .unwrap();
    println!("Melted data (better for analysis):");
    println!("{}\n", revenue_long);

    // ========== REAL-WORLD EXAMPLE ==========
    println!("\n=== REAL-WORLD EXAMPLE - Store Performance ===\n");

    // Daily sales by store and department
    let store_sales = DataFrame::builder()
        .add_column("store", vec![1.0, 1.0, 1.0, 2.0, 2.0, 2.0, 3.0, 3.0, 3.0])
        .add_column(
            "department",
            vec![1.0, 2.0, 3.0, 1.0, 2.0, 3.0, 1.0, 2.0, 3.0],
        )
        .add_column(
            "revenue",
            vec![
                1000.0, 1500.0, 2000.0, 1200.0, 1600.0, 2200.0, 900.0, 1400.0, 1900.0,
            ],
        )
        .add_column(
            "customers",
            vec![50.0, 75.0, 100.0, 60.0, 80.0, 110.0, 45.0, 70.0, 95.0],
        )
        .build()
        .unwrap();

    println!("Store performance data:");
    println!("{}\n", store_sales);

    // Analysis 1: Revenue by store and department
    println!("--- Revenue Matrix: Stores × Departments ---");
    let revenue_matrix = store_sales
        .pivot_table("store", "department", "revenue", "sum")
        .unwrap();
    println!("{}\n", revenue_matrix);

    // Analysis 2: Customer traffic by store and department
    println!("--- Customer Matrix: Stores × Departments ---");
    let customer_matrix = store_sales
        .pivot_table("store", "department", "customers", "sum")
        .unwrap();
    println!("{}\n", customer_matrix);

    // Analysis 3: Average revenue per customer
    println!("--- Average Revenue per Customer: Stores × Departments ---");
    let avg_per_customer = store_sales
        .pivot_table("store", "department", "revenue", "mean")
        .unwrap();
    println!("{}\n", avg_per_customer);

    // ========== PIVOT vs MELT ROUNDTRIP ==========
    println!("\n=== ROUNDTRIP: Pivot → Melt → Original ===\n");

    println!("1. Start with LONG format:");
    let original = DataFrame::builder()
        .add_column("id", vec![1.0, 1.0, 2.0, 2.0])
        .add_column("category", vec![1.0, 2.0, 1.0, 2.0])
        .add_column("value", vec![10.0, 20.0, 30.0, 40.0])
        .build()
        .unwrap();
    println!("{}\n", original);

    println!("2. Pivot to WIDE format:");
    let pivoted = original
        .pivot_table("id", "category", "value", "sum")
        .unwrap();
    println!("{}\n", pivoted);

    println!("3. Melt back to LONG format:");
    let melted = pivoted.melt(&["id"], None, "category", "value").unwrap();
    println!("{}\n", melted);

    // ========== USE CASES ==========
    println!("\n=== COMMON USE CASES ===\n");

    println!("✅ PIVOT TABLE:");
    println!("  - Sales reports (products × regions)");
    println!("  - Time series analysis (dates × metrics)");
    println!("  - Cross-tabulation (demographics × behavior)");
    println!("  - Dashboard summaries");
    println!("  - Excel-style pivot tables");

    println!("\n✅ MELT:");
    println!("  - Prepare spreadsheet data for analysis");
    println!("  - Normalize denormalized data");
    println!("  - Convert wide to long for plotting");
    println!("  - Database import preparation");
    println!("  - Time series from wide format");

    println!("\n=== AGGREGATION FUNCTIONS AVAILABLE ===");
    println!("  • sum     - Total");
    println!("  • mean    - Average");
    println!("  • count   - Number of records");
    println!("  • min     - Minimum value");
    println!("  • max     - Maximum value");
    println!("  • median  - Middle value");

    println!("\n=== Demo Complete! ===");
}