Sample pandas code

gistfile1.txt

import pandas as pd

# Load the data from the CSV file
df = pd.read_csv("weather_data.csv")

# Group by city and calculate the max and mean temperatures for both temperature_f and temperature_c
agg_data_f = df.groupby("city")["temperature_f"].agg(["max", "min", "mean"])
agg_data_c = df.groupby("city")["temperature_c"].agg(["max", "min", "mean"])

# Get fluctuation per city
fluctuation_temp_f = agg_data_f["max"] - agg_data_f["min"]
fluctuation_temp_c = agg_data_c["max"] - agg_data_c["min"]

# Give names to the Series
fluctuation_temp_f.name = "Fluctuation Temperature (F)"
fluctuation_temp_c.name = "Fluctuation Temperature (C)"

# Only show data required
agg_data_f = agg_data_f.drop(columns=["min"])
agg_data_c = agg_data_c.drop(columns=["min"])

# Rename columns for clarity
agg_data_f.columns = ["Max Temperature (F)", "Mean Temperature (F)"]
agg_data_c.columns = ["Max Temperature (C)", "Mean Temperature (C)"]

# Get the date corresponding to the highest temperature for temperature_f
highest_temp_dates_f = df.loc[df.groupby("city")["temperature_f"].idxmax()][["city", "date"]]
highest_temp_dates_f = highest_temp_dates_f.rename(columns={"date": "Date of Max Temperature"})

# Merge all the data: max/mean for temperature_f, max/mean for temperature_c, and the date of highest temperature
combined_data = pd.merge(agg_data_f, agg_data_c, on="city")
combined_data = pd.merge(combined_data, highest_temp_dates_f, on="city")

# Display the result
print(combined_data)


# Merge all fluctuation temperature data
combined_data_fluctuation = pd.merge(fluctuation_temp_f,fluctuation_temp_c, on="city")
print(combined_data_fluctuation)