From 7cb5b392d171bed9e5016815e9e0b4999971e475 Mon Sep 17 00:00:00 2001
From: matt <git@publicmatt.com>
Date: Mon, 5 Jun 2023 10:19:53 -0700
Subject: [PATCH] add hw assignment 1

---
 src/hw/assignment1.py | 62 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 src/hw/assignment1.py

diff --git a/src/hw/assignment1.py b/src/hw/assignment1.py
new file mode 100644
index 0000000..58a14f8
--- /dev/null
+++ b/src/hw/assignment1.py
@@ -0,0 +1,62 @@
+import click
+from dotenv import load_dotenv
+from data.main import paths, connect
+import pandas as pd
+import math
+
+@click.group()
+def cli():
+    ...
+
+@cli.command('hw1:simple')
+def simple_mean():
+    data = pd.read_csv(paths('data') / 'hw' / 'q1.csv', sep="|").sort_values('salary').reset_index(drop=True)
+    mean = sum(data.salary) / len(data.salary)
+    print(f"mean: {mean:.1f}")
+
+    count = data.groupby('salary')['salary'].count()
+    weighted_mean = sum([a * b for a, b in zip(list(count.index), list(count))]) / len(data)
+    print(f"weighted: {weighted_mean:.1f}")
+
+    total = 1
+    for i in data.salary:
+        total *= i
+    geometric = total ** (1 / len(data))
+    print(f"geometric: {geometric:.1f}")
+
+    median = data.iloc[len(data) // 2]['salary']
+    print(f"median: {median}")
+
+    counts = dict(zip(list(count.index), list(count)))
+    mode = max(counts, key=counts.get)
+    print(f"mode: {mode}")
+
+    variance = sum(((data - mean) ** 2)['salary']) / len(data)
+    print(f"variance: {variance:.1f}")
+
+    std = math.sqrt(variance)
+    print(f"std: {std:.2f}")
+
+    z_scores = round((data - mean) / std, 2)
+    z_scores = list(zip(data.salary, z_scores.salary))
+    print(f"z_scores: {z_scores}")
+
+
+    coeff_v = std / mean * 100
+    print(f"coeff. of var.: {coeff_v:.2f}%")
+
+    q_1 = data.iloc[len(data) // 4]['salary']
+    print(f"first quartile: {q_1}")
+
+    q_3 = data.iloc[(len(data) // 4) * 3]['salary']
+    print(f"third quartile: {q_3}")
+
+
+    data = pd.read_csv(paths('data') / 'hw' / 'a1_q2.csv', sep="|")
+    mode = (3 *data['median']) - (2 * data['mean'])
+    print(f"mode: {mode.values}")
+
+
+if __name__ == "__main__":
+    load_dotenv()
+    cli()