From 5d121f66af7f67fd1261165ee574a52e539fc4d6 Mon Sep 17 00:00:00 2001
From: cynic <admin@cynic.moe>
Date: Thu, 14 Jul 2022 05:57:25 -0400
Subject: [PATCH] mean heuristic test

---
 .gitignore |  1 +
 main.py    | 44 ++++++++++++++++++++++++++++++++++++++++++++
 test.py    | 11 +++++++++++
 3 files changed, 56 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 test.py

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..16f2dc5
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+*.csv
\ No newline at end of file
diff --git a/main.py b/main.py
index 7d07b1f..de575ff 100644
--- a/main.py
+++ b/main.py
@@ -6,3 +6,47 @@ except FileNotFoundError:
     print("downloading dataset...")
     txt = get("https://the.silly.computer/creditcard.csv").text
     open("creditcard.csv", "w").write(txt)
+
+data = pandas.read_csv("creditcard.csv")
+data['mean'] = data.mean(axis=1)
+
+fraud_set = data.loc[data["Class"] == 1]
+legit_set = data.loc[data["Class"] == 0]
+
+good_heuristics = []
+
+for col_name in fraud_set.columns:
+    fm = fraud_set[col_name].mean()
+    lm = legit_set[col_name].mean()
+    corr = 0
+    incorr = 0
+    for r in data.iterrows():
+        if abs(r[1][col_name] - fm) < abs(r[1][col_name] - lm):
+            if r[1]["Class"] == 1: corr += 1
+            else: incorr += 1
+        elif abs(r[1][col_name] - fm) > abs(r[1][col_name] - lm):
+            if r[1]["Class"] == 0: corr += 1
+            else: incorr += 1
+            
+    print(col_name)
+    print(fm)
+    print(lm)
+    accuracy = corr/(corr+incorr)
+    print(accuracy)
+    if (accuracy > .98) and col_name != "Class":
+        print("good heuristic!")
+        good_heuristics.append({"name": col_name, "fraud_mean": fm, "legit_mean": lm})
+    print("")
+
+print(good_heuristics)
+
+guessed_class = []
+for r in data.iterrows():
+    good = True
+    for h in good_heuristics:
+        if abs(r[1][h["name"]] - h["fraud_mean"]) < abs(r[1][h["name"]] - h["legit_mean"]):
+            good = False
+    guessed_class.append(0 if good else 1)
+data["guess"] = guessed_class
+print(data.head(10))
+data.to_csv("woo.csv")
\ No newline at end of file
diff --git a/test.py b/test.py
new file mode 100644
index 0000000..2b375ce
--- /dev/null
+++ b/test.py
@@ -0,0 +1,11 @@
+import pandas
+data = pandas.read_csv("creditcard.csv")
+guessed_class = []
+for r in data.iterrows():
+    good = True
+    if abs(r[1]["V17"] - -6.665836399449663) < abs(r[1]["V17"] - 0.01153506325212925):
+        good = False
+    guessed_class.append(0 if good else 1)
+data["guess"] = guessed_class
+print(data.head(10))
+data.to_csv("woo2.csv")
\ No newline at end of file