fixed so txs are (more) uniformly distributed over steps

aidotse · Nov 9, 2023 · 3b16498 · 3b16498
1 parent 837c6bb
commit 3b16498
Show file tree

Hide file tree

Showing 5 changed files with 415 additions and 11 deletions.
diff --git a/AMLsim/src/main/java/amlsim/AccountGroup.java b/AMLsim/src/main/java/amlsim/AccountGroup.java
@@ -22,17 +22,28 @@ public class AccountGroup {
         assert startStep < endStep : "startStep must be smaller than endStep";
         assert interval > 0 : "interval must be positive";
 
-        if (startStep >= 0 && startStep < AMLSim.getNumOfSteps()) {
-            int range = (int) (endStep - startStep + 1);
-            this.startStep = AMLSim.getRandom().nextInt(range) + startStep;
-        } else {
-            this.startStep = AMLSim.getRandom().nextInt((int) AMLSim.getNumOfSteps() - 1);
+        //if (startStep >= 0 && startStep < AMLSim.getNumOfSteps()) {
+        //    int range = (int) (endStep - startStep + 1);
+        //    this.startStep = AMLSim.getRandom().nextInt(range) + startStep;
+        //} else {
+        //    this.startStep = AMLSim.getRandom().nextInt((int) AMLSim.getNumOfSteps() - 1);
+        //}
+        //
+        //if (endStep >= 0 && endStep < AMLSim.getNumOfSteps()) {
+        //    this.endStep = endStep;
+        //} else {
+        //    this.endStep = AMLSim.getNumOfSteps();
+        //}
+
+        long s1 = startStep + AMLSim.getRandom().nextInt((int) (endStep - startStep + 1));
+        long s2 = startStep + AMLSim.getRandom().nextInt((int) (endStep - startStep + 1));
+        this.startStep = Math.min(s1, s2);
+        this.endStep = Math.max(s1, s2);
+        if (this.startStep < startStep) {
+            this.startStep = startStep;
         }
-
-        if (endStep >= 0 && endStep < AMLSim.getNumOfSteps()) {
+        if (this.endStep > endStep) {
             this.endStep = endStep;
-        } else {
-            this.endStep = AMLSim.getNumOfSteps();
         }
 
         this.scheduleID = scheduleID;

diff --git a/transaction-network-explorer/TransactionNetwork.py b/transaction-network-explorer/TransactionNetwork.py
@@ -31,6 +31,7 @@ def __init__(self, path:str) -> None:
 
     def load_data(self, path:str) -> pd.DataFrame:
         df = pd.read_csv(path)
+        df = df.loc[df['type']!='CASH']
         return df
 
     def format_data(self, df:pd.DataFrame) -> pd.DataFrame:

diff --git a/transaction-network-explorer/__pycache__/TransactionNetwork.cpython-310.pyc b/transaction-network-explorer/__pycache__/TransactionNetwork.cpython-310.pyc
diff --git a/transaction-network-explorer/test.ipynb b/transaction-network-explorer/test.ipynb
@@ -0,0 +1,110 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>step</th>\n",
+       "      <th>acct</th>\n",
+       "      <th>amt</th>\n",
+       "      <th>bal</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>a</td>\n",
+       "      <td>10</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>1</td>\n",
+       "      <td>a</td>\n",
+       "      <td>-10</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>5</td>\n",
+       "      <td>a</td>\n",
+       "      <td>10</td>\n",
+       "      <td>10</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   step acct  amt  bal\n",
+       "0     0    a   10   10\n",
+       "5     1    a  -10    0\n",
+       "1     5    a   10   10"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "steps = [0, 5, 2, 3, 4, 1]\n",
+    "accts = ['a', 'a', 'b', 'b', 'b', 'a']\n",
+    "amts = [10, 10, 10, -10, 10, -10]\n",
+    "df = pd.DataFrame({'step': steps, 'acct': accts, 'amt': amts})\n",
+    "\n",
+    "df = df.sort_values(by=['step'])\n",
+    "df['bal'] = df.groupby('acct')['amt'].cumsum()\n",
+    "\n",
+    "df[df['acct']=='a']\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "tne-cpu",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}