import numpy as np
import matplotlib.pyplot as plt
import csv
data_file_name = "One year temperature in Seoul.csv"
f = open(data_file_name)
temp_data = csv.reader(f)
temp_month = [[], [], [], [], [], [], [], [], [], [], [], []]
for row in temp_data:
if row[4] != '':
m = int(row[0].split('-')[1])-1
temp_month[m].append(float(row[4]))
I'm just doing it, but I don't know what to do...ㅜ Please let me know
python csv numpy
I didn't know what format of data was in the csv file, so I gave an example arbitrarily. Wouldn't it be similar?
Is there a reason why I have to use numpy instead of pandas? Like csv, tabular data is much more convenient to manipulate with pandas rather than numpy.
import pandas as pd
"""
Assume that the Seoul_temperature.csv file looks like this:
date | celsius
---------------
2020-01-01 | -17
2020-01-02 | -15
.
.
.
2020-05-23 | 14.5
2020-05-24 | 15.3
"""
# Step 1. Read CSV
df = pd.read_csv("./Seoul_temperature.csv") # Replace with the path where the TODOcsv file is located!
# Step 2. Switch date string to datetime object
df['date'] = df['date'].apply(lambda x: pd.to_datetime(x, format='%Y-%m-%d'))
# Step 3. To find the highest monthly temperature, create a new "year-month" tag
df['ym'] = df['date'].apply(lambda x: x.strftime("%Y-%m"))
print ("=== Daily Data ===")
print(df)
# Step 4. Find the variance of daily temperature
variation = df['celsius'].var()
print("===Daily data variance===")
print(variation)
# Step 5. Create a new monthly_df with the highest temperature per month and print it
monthly_df = df.groupby('ym').agg({'celsius': 'max'})
print("===Monthly maximum temperature ===")
print(Monthly_df) # The highest monthly temperature is organized and printed.
© 2024 OneMinuteCode. All rights reserved.