day2 intermediate code

src/T08_WorldCities.py

@@ -1,11 +1,99 @@
-import pandas
+from typing import Optional
+
 import pandas as pd
+from numpy.f2py.crackfortran import true_intent_list
 
-world_cities = pd.read_excel("../data/worldcities.xlsx")
-print(world_cities)
-print(world_cities.columns)
-print(f"{world_cities['city']}")
 
+def get_population_of_country(df, country):
+    """
+    Get the summed population of all cities in a given country.
+    :param df: Dataframe, must contain country and population as columns.
+    :param country: string, name of the country, case-senstive
+    :return: float: Final Population
+    :raises: KeyError if column is missing
+    """
+    cities = df[df["country"] == country]
+    return cities["population"].sum()
+
+def get_cities_beyond_latitude(df, lat, north=True):
+    """
+    Get all rows where latitude is either north or south of given latitude.
+    :param df:
+    :param lat:   Breitengrad
+    :param north: north is >= and !north <
+    :return: Dataframe
+    """
+    if north:
+        return df[df['lat'] >= lat]
+    return df[df['lat'] < lat]
+
+
+def get_larger_cities_north_of_city_conditions(df, city: str, **cmp_cols):
+    mask = df["city"] == city
+    for col_name, col_value in cmp_cols.items():
+        mask &= df[col_name] == col_value
+    row = df[mask]
+    if len(row) > 1:
+        raise ValueError(f"Search not unique. found: {row}")
+    # Achtung potentiel mehr als eine Zeile
+    latitude = row['lat'].iloc[0]
+    population = row['population'].iloc[0]
+    cities_north = get_cities_beyond_latitude(df, latitude, north=True)
+    cities_north = cities_north[cities_north['population'] > population]
+    return cities_north
+
+def get_larger_cities_north_of_city(df, city: str, country: Optional[str]=None):
+    if country:
+        return get_larger_cities_north_of_city_conditions(
+            df, city, country=country
+        )
+    return get_larger_cities_north_of_city_conditions(
+        df, city
+    )
+
+
+if __name__ == "__main__":
+    print("Country Population")
+    world_cities = pd.read_excel("../data/worldcities.xlsx")
+    print(world_cities.columns)
+    german_population = get_population_of_country(world_cities, "Germany")
+    print(f"Population of Germany: {german_population}")
+    narnia_population = get_population_of_country(world_cities, "Narnia")
+    print(f"Population of Narnia: {narnia_population}")
+
+    print("-"*100)
+    print("North-South Population")
+    # nord/süd
+    north = get_cities_beyond_latitude(world_cities, 0, north=True)
+    print(north["population"].sum())
+    south = get_cities_beyond_latitude(world_cities, 0, north=False)
+    print(south["population"].sum())
+    print("-" * 100)
+    print("Cities north of")
+    cities_north_of_berlin = get_larger_cities_north_of_city(world_cities,
+                                                      "Berlin",
+                                                      "Germany")
+    print(cities_north_of_berlin)
+    cities = ["New York", "Istanbul"]
+    for city in cities:
+        northern_cities = get_larger_cities_north_of_city(world_cities,
+                                                   city)
+        print(f"Cities north of: {city}")
+        print(northern_cities)
+    try:
+        northern_cities = get_larger_cities_north_of_city(world_cities,
+                                                   "Rome")
+        print("Error should have happened")
+    except ValueError:
+        print("Expected ValueError: Rome multiple times in world_cities")
+
+    print(world_cities[world_cities["city"] == "Rome"])
+    northern_cities = get_larger_cities_north_of_city_conditions(
+        world_cities,
+        "Rome",
+        capital="primary",
+    )
+    print(northern_cities)
 # conda install openpyxl
 # 1) Wie viele Einwohner haben alle Deutschen Städte?
 #                                     XYZ
@@ -20,6 +108,3 @@ print(f"{world_cities['city']}")
 # funktion
 #  -> raise
 #  -> assert
-
-val = world_cities[(world_cities["city"] == "Berlin") & (world_cities["country"] == "Germany")]["population"].iloc[0]
-print(type(val))

src/T09_GroupBy.py

@@ -0,0 +1,45 @@
+import pandas as pd
+
+beverages = pd.read_csv("../data/beverages.csv")#
+print(beverages)
+
+
+# 1) Funktion
+groups = beverages.groupby("Name").max()
+print(groups)
+
+groups = beverages.groupby("Name") # kategorisches
+print(groups)
+
+print(groups.max())
+print(groups.min())
+print()
+for name, info in groups:
+    # name ist die Kategorie nach der gruppiert wurde
+    # info sind alle Zeilen die zu dieser Kategorie gehören
+    print(name)
+    print(info)
+    print("-"*100)
+    print()
+
+print()
+# print(help(pd.read_csv))
+donations_df = pd.read_csv("../data/donations.csv")
+print(donations_df)
+
+subset = donations_df[["city", "job", "income", "donations"]]
+grouped_donations = subset.groupby(["job", "city"]).mean().round()
+print(grouped_donations)
+print("-"*100)
+print(grouped_donations.loc["Student"].loc[["Hamburg", "Köln"]])
+# zeile students ist wieder ein dataframe
+students = grouped_donations.loc["Student"]
+print(students.loc["Hamburg"])
+print("-"*100)
+# doppelte indizes
+info = grouped_donations.unstack()
+income = info["income"]
+don = info["donations"]
+print(income)
+print(don)
+print()

src/T10_ex_Energy.py

@@ -0,0 +1,16 @@
+import pandas as pd
+
+energy_df = pd.read_csv("../data/germany_energy_mix_2019_2024.csv")
+print(energy_df)
+print(energy_df.columns)
+
+# Green, Non-Green
+
+# 1) Wiewiel erneuerbare bzw nicht-erneuerbare energie wurde insgesamt produziert
+# 2) Pro Jahr  (unstack)
+
+# 3) jährlich nach Energy_Source angeben
+# 4) welche energiequelle hat den größten/kleinsten wachstum  (idxmax)
+# 5) Prozentual
+#  Monatlichen Verlauf (Jan 2019 und Jan 2020 sind verschiedene)
+# In welchen monaten wurde mehr grüner als nicht-grüner strom produziert