——Exploring the “Ontario Climate Change Data Portal”: A Case Study in Data Exploration

Prompts searchable table

Examples

Download csv file from internet

ChatGPT prompt

I want you to act as a Python developer tasked with downloading a CSV file from the internet using the provided URL: https://lamps.math.yorku.ca/OntarioClimate/data/content/grids/Historical/Monthly_2m_temperature_8964_ERA5_January1981toMarch2021.csv.

To accomplish this, write a Python script that uses built-in functions or libraries to download the CSV file from the given URL. You can use the requests library to make an HTTP request to the URL and then save the contents of the response to a local CSV file on your computer.

Be sure to handle any errors that may occur during the download process, such as network errors or incorrect URL formats. Once you have successfully downloaded the CSV file, you can use Python's built-in functions or libraries to analyze the data and extract any useful information you need.

Generated python code

import requests

url = 'https://lamps.math.yorku.ca/OntarioClimate/data/content/grids/Historical/Monthly_2m_temperature_8964_ERA5_January1981toMarch2021.csv'
filename = 'temperature_data.csv'

try:
    response = requests.get(url)
    response.raise_for_status() # raise an exception if the status is not 200 (i.e. success)
    with open(filename, 'wb') as f:
        f.write(response.content) # write the contents of the response to a file
    print(f"File {filename} downloaded successfully.")
except requests.exceptions.RequestException as e:
    print(f"Error downloading file from {url}: {e}")

Download a csv file with no header and add new header and row names to the csv file

ChatGPT prompt

I want you to act as a Python developer tasked with downloading a CSV file from the internet using the provided URL: https://lamps.math.yorku.ca/OntarioClimate/DS_CMIP5/LAMPS_YorkU/Stations/AJAX/tas/RCP26/tas_CORDEX_RCP26_0.44_RCA4_EC_EARTH_365X120.csv. Once the CSV file is downloaded, your task is to add column and row names to the data based on the year and day of the year.

To accomplish this, write a Python script that uses built-in functions or libraries to download the CSV file from the given URL. You can use the requests library to make an HTTP request to the URL and then save the contents of the response to a local CSV file on your computer.

Since the CSV file has no header, you can use the pandas library to read in the contents of the file and add the appropriate column and row names to the data. You can use the read_csv() function from pandas to read in the contents of the CSV file, and then use the set_axis() method to set the appropriate column and row names. Since the file contains 120 columns representing years from 1981 to 2100, you can add column names with the year as 1981, 1982,...2020, and so on. Similarly, since the file contains 365 rows representing day 1 to day 365 of a year, you can add row names as 1, 2,...,365.

Be sure to handle any errors that may occur during the download or parsing process, such as network errors or incorrect file formats. By adding column and row names to the data, you can make it easier to analyze and understand the data, and you can more easily refer to specific days or years in the data.

ChatGPT generated Python code

import pandas as pd
import requests

url = "https://lamps.math.yorku.ca/OntarioClimate/DS_CMIP5/LAMPS_YorkU/Stations/AJAX/tas/RCP26/tas_CORDEX_RCP26_0.44_RCA4_EC_EARTH_365X120.csv"

try:
    # Make an HTTP request to the URL and get the contents of the response
    response = requests.get(url)
    response.raise_for_status()

    # Save the contents of the response to a local CSV file on your computer
    with open("data.csv", "w") as file:
        file.write(response.text)

    # Read in the contents of the CSV file using pandas and set the appropriate column and row names
    df = pd.read_csv("data.csv", header=None)
    column_names = [str(year) for year in range(1981, 2101)]
    row_names = [str(day) for day in range(1, 366)]
    df.set_axis(column_names, axis=1, inplace=True)
    df.set_axis(row_names, axis=0, inplace=True)

    # Write the updated data to a new CSV file
    df.to_csv("updated_data.csv")
except Exception as e:
    print(f"An error occurred: {e}")

Download csv file from internet and display general information of the data

ChatGPT prompt

I want you to act as a Python developer tasked with downloading a CSV file from the internet using the provided URL: https://lamps.math.yorku.ca/OntarioClimate/data/content/grids/Historical/Monthly_2m_temperature_8964_ERA5_January1981toMarch2021.csv. Once the CSV file is downloaded, your task is to display general information about the file.

To accomplish this, write a Python script that uses built-in functions or libraries to download the CSV file from the given URL. You can use the requests library to make an HTTP request to the URL and then save the contents of the response to a local CSV file on your computer.

Once you have downloaded the CSV file, you can use Python's built-in csv library to read in the contents of the file and extract information about its structure. For example, you could display the number of rows and columns in the file, the names of the columns, the data types of each column, and any missing or null values.

Be sure to handle any errors that may occur during the download or parsing process, such as network errors or incorrect file formats. By displaying general information about the CSV file, you can gain a better understanding of the data it contains and how it can be used in future analyses.

ChatGPT generated python code

import requests
import csv

# URL of the CSV file
url = 'https://lamps.math.yorku.ca/OntarioClimate/data/content/grids/Historical/Monthly_2m_temperature_8964_ERA5_January1981toMarch2021.csv'

# Download the CSV file from the URL and save it to a local file
response = requests.get(url)
with open('monthly_temperature.csv', 'wb') as f:
    f.write(response.content)

# Read in the CSV file and extract information about its structure
with open('monthly_temperature.csv', 'r') as f:
    reader = csv.reader(f)
    headers = next(reader)
    num_rows = sum(1 for row in reader)
    num_cols = len(headers)
    print(f"Number of rows: {num_rows}")
    print(f"Number of columns: {num_cols}")
    print(f"Column names: {headers}")

Plot spatial points stored in a csv file on internet

ChatGPT prompt

I want you to act as a data analyst tasked with analyzing a CSV file stored at a given URL. Specifically, your task is to read in the CSV file and display its data structure using Python. The CSV file located at https://lamps.math.yorku.ca/OntarioClimate/content/DataDownload/LAMPS_Ontario_8964Pts.csv contains the longitude and latitude of 8964 points that you need to analyze.

To accomplish this, write a Python script that reads the CSV file from the URL, then uses built-in functions or libraries to display information about the file's data structure, such as the number of rows and columns, data types, and any missing or null values. Be sure to consider ways to handle any errors that may occur during the reading or parsing of the CSV file.

Once you have successfully read in and analyzed the CSV file, use the Python package Cartopy to plot the longitude and latitude points onto a map. This will allow you to visualize the spatial distribution of the points and identify any patterns or trends that may be present.

ChatGPT generated python code

import pandas as pd
import numpy as np
import cartopy.crs as ccrs
import matplotlib.pyplot as plt
import urllib.request

# Define URL
url = 'https://lamps.math.yorku.ca/OntarioClimate/content/DataDownload/LAMPS_Ontario_8964Pts.csv'

# Read CSV file from URL
try:
    data = pd.read_csv(urllib.request.urlopen(url))
except Exception as e:
    print("Error reading CSV file:", e)

# Display data structure
print("Data shape:", data.shape)
print("Data types:\n", data.dtypes)
print("Missing values:\n", data.isnull().sum())

# Plot data points
plt.figure(figsize=(12, 8))
ax = plt.axes(projection=ccrs.PlateCarree())
ax.coastlines(resolution='10m')
plt.scatter(data['Longitude'], data['Latitude'], s=1, c='red')
plt.title('Longitude and Latitude of 8964 points in Ontario')
plt.show()

Calculate monthly mean from daily data

ChatGPT prompt

I want you to act as a data analyst and write a Python code to calculate the monthly mean temperature from the daily temperature data stored in a CSV file. The CSV file is located at the following URL: https://lamps.math.yorku.ca/OntarioClimate/DS_CMIP5/LAMPS_YorkU/Stations/AJAX/tas/RCP26/tas_CORDEX_RCP26_0.44_RCA4_EC_EARTH_365X120.csv. The daily temperature data is represented by 120 columns, each column represents a year, and there are 365 rows for each day of the year. You should assume that each year has 365 days and there is no leap year. The number of days in each month is as follows: January (31 days), February (28 days), March (31 days), April (30 days), May (31 days), June (30 days), July (31 days), August (31 days), September (30 days), October (31 days), November (30 days), and December (31 days).

After calculating the monthly mean temperature, you should save the data to a new CSV file with the name "MonthlyMeanTemperature.csv". The output CSV file should have 12 columns representing each month (January, February, ..., December) and 120 rows representing each year (1981, 1982, ..., 2100). As a data analyst, you should also make sure to include any necessary libraries and handle any potential errors that may arise during the data analysis process.

ChatGPT generated python code

import pandas as pd
import calendar

# Read the CSV file
url = "https://lamps.math.yorku.ca/OntarioClimate/DS_CMIP5/LAMPS_YorkU/Stations/AJAX/tas/RCP26/tas_CORDEX_RCP26_0.44_RCA4_EC_EARTH_365X120.csv"
df = pd.read_csv(url)

# Initialize a list to store the monthly means
monthly_means = []

# Loop over each year
for year in range(1981, 2101):
    # Initialize a list to store the monthly means for the current year
    year_means = []
    # Loop over each month
    for month in range(1, 13):
        # Calculate the number of days in the current month
        num_days = calendar.monthrange(year, month)[1]
        # Get the daily temperatures for the current month and year
        month_temps = df.iloc[(month-1)*num_days:month*num_days, year-1981].values
        # Calculate the mean temperature for the current month and year
        month_mean = month_temps.mean()
        # Append the monthly mean temperature to the list for the current year
        year_means.append(month_mean)
    # Append the list of monthly means for the current year to the list of all monthly means
    monthly_means.append(year_means)

# Convert the list of monthly means to a DataFrame
monthly_means_df = pd.DataFrame(monthly_means)

# Add column names for each month
monthly_means_df.columns = calendar.month_name[1:]

# Save the monthly means to a new CSV file
monthly_means_df.to_csv("MonthlyMeanTemperature.csv", index=False)

Note: Instead of using the monthly mean, you can choose to use other statistical functions provided by pandas such as monthly maximum, monthly minimum, or other similar functions.

To be updated frequently