update the iterative solution

CITATION.cff

@@ -6,6 +6,8 @@ authors:
   given-names: "Radovan"
 - family-names: "Darst"
   given-names: "Richard"
+- family-names: "Tian"
+  given-names: "Yu"
 - family-names:  "Juselius"
   given-names: "Jonas"
 - family-names: "Di Remigio Eikås"

content/code/abstracting-plot.py

@@ -1,31 +1,66 @@
 import pandas as pd
-from matplotlib import pyplot as plt
+import matplotlib.pyplot as plt
 
-plt.xlabel("measurements")
-plt.ylabel("air temperature (deg C)")
 
+def plot(column, label, location, color, compute_mean):
+    fig, ax = plt.subplots()
 
-def plot_temperatures(temperatures):
-    plt.plot(temperatures, "r-")
-    plt.axhline(y=mean, color="b", linestyle="--")
-    plt.show()
-    plt.savefig(f"{num_measurements}.png")
-    plt.clf()
+    # time series
+    ax.plot(
+        data_month.index,
+        data_month[column],
+        label=label,
+        color=color,
+    )
 
+    if compute_mean:
+        values = data_month[column].values
+        mean_value = sum(values) / len(values)
 
-for num_measurements in [25, 100, 500]:
+        # mean (as horizontal dashed line)
+        ax.axhline(
+            y=mean_value,
+            label=f"mean {label}: {mean_value:.1f}",
+            color=color,
+            linestyle="--",
+        )
 
-    # read data from file
-    data = pd.read_csv("temperatures.csv", nrows=num_measurements)
-    temperatures = data["Air temperature (degC)"]
+    ax.set_title(f"{label} at {location}")
+    ax.set_xlabel("date and time")
+    ax.set_ylabel(label)
+    ax.legend()
+    ax.grid(True)
 
-    # compute statistics
-    mean = sum(temperatures) / num_measurements
+    # format x-axis for better date display
+    fig.autofmt_xdate()
 
-    # plot results
-    #   plt.plot(temperatures, 'r-')
-    #   plt.axhline(y=mean, color='b', linestyle='--')
-    #   plt.show()
-    #   plt.savefig(f'{num_measurements}.png')
-    #   plt.clf()
-    plot_temperatures(temperatures)
+    fig.savefig(f"{month}-{column}.png")
+
+
+# read data
+data = pd.read_csv("weather_data.csv")
+
+# combine 'date' and 'time' into a single datetime column
+data["datetime"] = pd.to_datetime(data["date"] + " " + data["time"])
+
+# set datetime as index for convenience
+data = data.set_index("datetime")
+
+
+for month in ["2024-01", "2024-02", "2024-03"]:
+    data_month = data.loc[month]
+
+    plot(
+        "air_temperature_celsius",
+        "air temperature (C)",
+        "Helsinki airport",
+        "red",
+        compute_mean=True,
+    )
+    plot(
+        "precipitation_mm",
+        "precipitation (mm)",
+        "Helsinki airport",
+        "blue",
+        compute_mean=False,
+    )

content/code/add-iteration.py

@@ -1,21 +1,69 @@
 import pandas as pd
-from matplotlib import pyplot as plt
+import matplotlib.pyplot as plt
 
-plt.xlabel("measurements")
-plt.ylabel("air temperature (deg C)")
 
-for num_measurements in [25, 100, 500]:
+# read data
+data = pd.read_csv("weather_data.csv")
 
-    # read data from file
-    data = pd.read_csv("temperatures.csv", nrows=num_measurements)
-    temperatures = data["Air temperature (degC)"]
+# combine 'date' and 'time' into a single datetime column
+data["datetime"] = pd.to_datetime(data["date"] + " " + data["time"])
 
-    # compute statistics
-    mean = sum(temperatures) / num_measurements
+# set datetime as index for convenience
+data = data.set_index("datetime")
 
-    # plot results
-    plt.plot(temperatures, "r-")
-    plt.axhline(y=mean, color="b", linestyle="--")
-    plt.show()
-    plt.savefig(f"{num_measurements}.png")
-    plt.clf()
+
+for month in ["2024-01", "2024-02", "2024-03"]:
+    data_month = data.loc[month]
+
+    fig, ax = plt.subplots()
+
+    # temperature time series
+    ax.plot(
+        data_month.index,
+        data_month["air_temperature_celsius"],
+        label="air temperature (C)",
+        color="red",
+    )
+
+    values = data_month["air_temperature_celsius"].values
+    mean_temp = sum(values) / len(values)
+
+    # mean temperature (as horizontal dashed line)
+    ax.axhline(
+        y=mean_temp,
+        label=f"mean air temperature (C): {mean_temp:.1f}",
+        color="red",
+        linestyle="--",
+    )
+
+    ax.set_title("air temperature (C) at Helsinki airport")
+    ax.set_xlabel("date and time")
+    ax.set_ylabel("air temperature (C)")
+    ax.legend()
+    ax.grid(True)
+
+    # format x-axis for better date display
+    fig.autofmt_xdate()
+
+    fig.savefig(f"{month}-temperature.png")
+
+    fig, ax = plt.subplots()
+
+    # precipitation time series
+    ax.plot(
+        data_month.index,
+        data_month["precipitation_mm"],
+        label="precipitation (mm)",
+        color="blue",
+    )
+
+    ax.set_title("precipitation (mm) at Helsinki airport")
+    ax.set_xlabel("date and time")
+    ax.set_ylabel("precipitation (mm)")
+    ax.legend()
+    ax.grid(True)
+
+    # format x-axis for better date display
+    fig.autofmt_xdate()
+
+    fig.savefig(f"{month}-precipitation.png")

content/code/cli.py

@@ -1,55 +1,109 @@
+from pathlib import Path
+
+
 import pandas as pd
-from matplotlib import pyplot as plt
+import matplotlib.pyplot as plt
 import pytest
 import click
 
 
-def plot_data(data, mean, xlabel, ylabel, file_name):
-    plt.plot(data, "r-")
-    plt.xlabel(xlabel)
-    plt.ylabel(ylabel)
-    plt.axhline(y=mean, color="b", linestyle="--")
-    plt.savefig(file_name)
-    plt.clf()
+def read_data(file_name):
+    data = pd.read_csv(file_name)
+
+    # combine 'date' and 'time' into a single datetime column
+    data["datetime"] = pd.to_datetime(data["date"] + " " + data["time"])
+
+    # set datetime as index for convenience
+    data = data.set_index("datetime")
 
+    return data
 
-def compute_mean(data):
-    mean = sum(data) / len(data)
-    return mean
 
+def arithmetic_mean(values):
+    mean_value = sum(values) / len(values)
+    return mean_value
 
-def test_compute_mean():
-    result = compute_mean([1.0, 2.0, 3.0, 4.0])
+
+def test_arithmetic_mean():
+    result = arithmetic_mean([1.0, 2.0, 3.0, 4.0])
     assert result == pytest.approx(2.5)
 
 
-def read_data(file_name, nrows, column):
-    data = pd.read_csv(file_name, nrows=nrows)
-    return data[column]
+def plot(date_range, values, label, location, color, compute_mean, file_name):
+    fig, ax = plt.subplots()
+
+    # time series
+    ax.plot(
+        date_range,
+        values,
+        label=label,
+        color=color,
+    )
+
+    if compute_mean:
+        mean_value = arithmetic_mean(values)
+
+        # mean (as horizontal dashed line)
+        ax.axhline(
+            y=mean_value,
+            label=f"mean {label}: {mean_value:.1f}",
+            color=color,
+            linestyle="--",
+        )
+
+    ax.set_title(f"{label} at {location}")
+    ax.set_xlabel("date and time")
+    ax.set_ylabel(label)
+    ax.legend()
+    ax.grid(True)
+
+    # format x-axis for better date display
+    fig.autofmt_xdate()
+
+    fig.savefig(file_name)
 
 
 @click.command()
+@click.option("--month", required=True, type=str, help="Which month (YYYY-MM)?")
 @click.option(
-    "--num-measurements", required=True, type=int, help="Number of measurements."
+    "--data-file",
+    required=True,
+    type=click.Path(exists=True, path_type=Path),
+    help="Data is read from this file.",
 )
-@click.option("--in-file", required=True, help="File name where we read from.")
-@click.option("--out-file", required=True, help="File name where we write to.")
-def main(num_measurements, in_file, out_file):
-
-    temperatures = read_data(
-        file_name=in_file,
-        nrows=num_measurements,
-        column="Air temperature (degC)",
-    )
+@click.option(
+    "--output-directory",
+    required=True,
+    type=click.Path(exists=True, path_type=Path),
+    help="Figures are written to this directory.",
+)
+def main(
+    month,
+    data_file,
+    output_directory,
+):
+    data = read_data(data_file)
 
-    mean = compute_mean(temperatures)
+    data_month = data.loc[month]
+    date_range = data_month.index
 
-    plot_data(
-        data=temperatures,
-        mean=mean,
-        xlabel="measurements",
-        ylabel="air temperature (deg C)",
-        file_name=out_file,
+    plot(
+        date_range,
+        data_month["air_temperature_celsius"].values,
+        "air temperature (C)",
+        "Helsinki airport",
+        "red",
+        compute_mean=True,
+        file_name=output_directory / f"{month}-temperature.png",
+    )
+    plot(
+        date_range,
+        data_month["precipitation_mm"].values,
+        "precipitation (mm)",
+        "Helsinki airport",
+        "blue",
+        compute_mean=False,
+        file_name=output_directory / f"{month}-precipitation.png",
     )
 
 

content/code/initial-version-with-mean.py

@@ -0,0 +1,47 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+
+
+# read data
+data = pd.read_csv("weather_data.csv")
+
+# combine 'date' and 'time' into a single datetime column
+data["datetime"] = pd.to_datetime(data["date"] + " " + data["time"])
+
+# set datetime as index for convenience
+data = data.set_index("datetime")
+
+# keep only january data
+january = data.loc["2024-01"]
+
+fig, ax = plt.subplots()
+
+# temperature time series
+ax.plot(
+    january.index,
+    january["air_temperature_celsius"],
+    label="air temperature (C)",
+    color="red",
+)
+
+values = january["air_temperature_celsius"].values
+mean_temp = sum(values) / len(values)
+
+# mean temperature (as horizontal dashed line)
+ax.axhline(
+    y=mean_temp,
+    label=f"mean air temperature (C): {mean_temp:.1f}",
+    color="red",
+    linestyle="--",
+)
+
+ax.set_title("air temperature (C) at Helsinki airport")
+ax.set_xlabel("date and time")
+ax.set_ylabel("air temperature (C)")
+ax.legend()
+ax.grid(True)
+
+# format x-axis for better date display
+fig.autofmt_xdate()
+
+fig.savefig("2024-01-temperature.png")