From 33871fba7728cf744c45a02f7ac73440b8abbb2e Mon Sep 17 00:00:00 2001
From: Hanzhang Ma <hanzhang@plunder.dbs.ifi.lmu.de>
Date: Mon, 13 May 2024 16:09:28 +0200
Subject: [PATCH] done with convert data

---
 read_data/convert_data.py | 75 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)
 create mode 100644 read_data/convert_data.py

diff --git a/read_data/convert_data.py b/read_data/convert_data.py
new file mode 100644
index 0000000..c5f5201
--- /dev/null
+++ b/read_data/convert_data.py
@@ -0,0 +1,75 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+
+import matplotlib.pyplot as plt
+import pandas as pd
+import numpy as np
+import os
+import csv
+
+def generate_min_df(mins = 15):
+    end = 60/mins * 24
+    start_date = '2023-01-01'
+    end_date = '2023-12-31'
+
+    all_dates = pd.date_range(start=start_date, end=end_date, freq='D')
+    all_times = pd.timedelta_range(start='0 min', end=f'1435 min', freq=f'{mins} min')
+
+    date_times = [pd.Timestamp(date) + time for date in all_dates for time in all_times]
+
+    time_frame = pd.DataFrame({
+        'Time': date_times
+    })
+    return time_frame
+
+def save_csv(df, filename, columns):
+    with open(filename, 'w', newline='') as file:
+        writer = csv.writer(file)
+        writer.writerow(['Time', 'PV yield[kW/kWp]'])
+        for index, row in df.iterrows():
+            time_formatted = index.strftime('%H:%M')
+            writer.writerow([time_formatted, row[columns[1]]])
+            
+        print(f'The file is written to {filename}')
+
+def read_csv(filename):
+    skip_rows = list(range(1, 17))
+    data = pd.read_csv(filename, sep=';', skiprows=skip_rows)
+    return data
+
+def process(file_name):
+    df = read_csv(file_name)
+    city = file_name.split('_')[0]
+
+    remain_column = ['Time','PV energy (AC) minus standby use ']
+    energy_row_name = remain_column[1]
+
+    df = df[remain_column]
+    df[energy_row_name] = df[energy_row_name].str.replace(',','.').astype(float)
+
+    sum_energy = df[energy_row_name].sum()
+    group_size = 15
+    df['group_id'] = df.index // group_size
+
+    sums = df.groupby('group_id')[energy_row_name].sum()
+    sums_df = sums.reset_index(drop=True).to_frame(name = 'Energy')
+
+    time_frame = generate_min_df(15)
+    sums_df = pd.concat([time_frame, sums_df], axis=1)
+    sums_df.set_index('Time', inplace=True)
+    max_value = sums_df['Energy'].max()
+    sums_df['Energy'] = sums_df['Energy'] / 390.
+    sums_df['Energy'] = sums_df['Energy'].round(4)
+    sums_df['Energy'].replace(0.0, -0.0)
+
+    save_csv(sums_df, f'{city}.csv', ['Time', 'Energy'])
+
+if __name__ == '__main__':
+    city_list = ['Riyahd', 'Cambodge', 'Berlin', 'Serbia']
+    for city in city_list:
+        print(f'Processing {city}')
+        file_name = f'{city}_raw.csv'
+        process(file_name)
+        print(f'Processing {city} is done\n')
+