From 6b9f0f1c69b03cd96a9d7579dcdbf26d7905ccab Mon Sep 17 00:00:00 2001
From: git-sandro <sandro-zimmermann@outlook.com>
Date: Thu, 23 Oct 2025 12:32:36 +0200
Subject: [PATCH] exercise_2.py finished

---
 exercise_2.py | 53 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/exercise_2.py b/exercise_2.py
index 735b429..03272f0 100644
--- a/exercise_2.py
+++ b/exercise_2.py
@@ -1,12 +1,65 @@
 import pandas as pd
+import matplotlib.pyplot as plt
+import datetime
 
 def load_dataframe():
     df = pd.read_excel("datasets/hardrock100_results_2022.xlsx", index_col=0)
     return df
 
+def time_str_to_seconds(time_object):
+    return time_object.second + time_object.minute * 60 + time_object.hour * 3600
+
+def calc_mean(df):
+    total_age = 0
+    for _, row in df.iterrows():
+        total_age += row["age"]
+    mean_age = total_age / len(df.index)
+    return mean_age
+
 def main():
     df = load_dataframe()
     print(df.head(3))
 
+    print(df.info()) # get column datatype
+
+    print(df[df["finish"].isna()]) # filter finish column -> not available
+
+    number_of_rows = len(df.index) # get number of rows
+    print(f"Number of rows: {number_of_rows}")
+
+    print(df.iloc[[5,8]]) # get place 5 & 8
+
+    print(f" Mean age: {calc_mean(df)}") # get mean age
+    print(df["age"].mean()) # alt get mean age
+
+    sorted_age = sorted(df["age"]) # sort column age
+    print(sorted_age)
+
+    # get median age
+    median_index = (number_of_rows -1) // 2
+    if number_of_rows % 2:
+        print(sorted_age[median_index])
+    else:
+        print((sorted_age[median_index] + sorted_age[median_index + 1])/2)
+    
+    print(df["age"].median()) # alt get median age
+    
+    print(df["age"].describe()) # 
+
+    # get time in seconds
+    time_str = "21:36:25"
+    time_object = datetime.datetime.strptime(time_str, "%H:%M:%S")
+    print(time_str_to_seconds(time_object))
+
+    na_value = datetime.time(0,0)
+    df["finish"] = df ["finish"].fillna(na_value)
+
+    df["finish_seconds"] = df["finish"].apply(time_str_to_seconds)
+
+    df.boxplot(column=["finish_seconds"])
+    plt.title("Verteilung der Zielzeiten in Sekunden")
+    plt.ylabel("Sekunden")
+    plt.show()
+
 if __name__ == "__main__":
     main()
\ No newline at end of file