From 141faba04fdd1b495481cba200e2eaba11f105f3 Mon Sep 17 00:00:00 2001
From: Kristofers Solo <kristians.cagulis@pm.me>
Date: Mon, 25 Dec 2023 18:48:20 +0200
Subject: [PATCH] calculate mean temp

---
 main.py | 70 +++++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 51 insertions(+), 19 deletions(-)

diff --git a/main.py b/main.py
index 8ac6ad1..06bcfad 100755
--- a/main.py
+++ b/main.py
@@ -3,7 +3,6 @@
 from pathlib import Path
 
 import matplotlib.pyplot as plt
-
 import numpy as np
 import pandas as pd
 from loguru import logger
@@ -21,25 +20,16 @@ WIND_GUSTS_PATH = BASE_PATH.joinpath("data", "vejaAtrumsBrazmas.xlsx")
 WIND_SPEED_PATH = BASE_PATH.joinpath("data", "vejaAtrumsFaktiskais.xlsx")
 AIR_TEMP_PATH = BASE_PATH.joinpath("data", "gaisaTemperatura2022.xlsx")
 
+BLUE = "#1f77b4"
+ORANGE = "#ff7f0e"
+BLACK = "#000000"
+
 
 def read_data(path: Path) -> pd.DataFrame:
-    dataframe = pd.read_excel(path, date_parser="Datums", index_col="Datums")
+    dataframe = pd.read_excel(path, parse_dates=["Datums"], index_col="Datums", date_format="%d.%m.%Y")
     return dataframe
 
 
-def get_season(month: int) -> str | None:
-    if month in [12, 1, 2]:
-        return "Ziema"
-    elif month in [3, 4, 5]:
-        return "Pavasaris"
-    elif month in [6, 7, 8]:
-        return "Vasara"
-    elif month in [9, 10, 11]:
-        return "Rudens"
-    else:
-        return None
-
-
 def bar_chart() -> None:
     df_avg = read_data(WIND_SPEED_PATH).mean(axis=1)
     df_max = read_data(WIND_GUSTS_PATH).max(axis=1) - df_avg
@@ -50,10 +40,10 @@ def bar_chart() -> None:
     )
 
     df_combined.columns = ["Vidējais", "Maksimālais"]
-    df_combined.plot.bar(stacked=True, figsize=(12, 8), color=["#ff7f0e", "#1f77b4"], width=0.6)
+    df_combined.plot.bar(stacked=True, figsize=(12, 8), color=[ORANGE, BLUE], width=0.6)
 
     plt.yticks(np.arange(0, df_combined.max().max() + 2.5, 2.5))
-    plt.xticks(rotation=45)
+    plt.xticks(rotation=45)  # FIX: don't display time
 
     plt.title("Vidējais un maksimālais vēja ātrums 2023. gada augustā")
     plt.xlabel("Mērījumu Datums")
@@ -71,14 +61,56 @@ SEASONS = {
 
 def box_plot() -> None:
     df = read_data(AIR_TEMP_PATH)
-    df.index = pd.to_datetime(df.index, format="%d.%m.%Y")
 
     df["Season"] = df.index.month % 12 // 3 + 1
     df["Season"] = df["Season"].map(SEASONS)
 
+    df["Average"] = df.iloc[:, 0:24].mean(axis=1)
+
+    df_melted = pd.melt(df, id_vars=["Season"], value_name="Temperature", var_name="Time")  # FIX: should be average temperature
+    df_melted["Season"] = pd.Categorical(df_melted["Season"], categories=SEASONS.values(), ordered=True)
+
+    _, ax = plt.subplots(figsize=(12, 8))
+
+    box_props = dict(facecolor=BLUE)  # box
+    median_props = dict(color=ORANGE)  # median line
+    whisker_props = dict(color=BLACK)  # whiskers (vertical line beween box and min/max)
+    width = 0.4
+
+    df_melted[df_melted["Season"] == "Rudens"].boxplot(
+        by="Season",
+        ax=ax,
+        grid=False,
+        showfliers=0.5,
+        boxprops=box_props,
+        medianprops=median_props,
+        whiskerprops=whisker_props,
+        patch_artist=True,
+        widths=width,
+    )
+
+    df_melted[df_melted["Season"] != "Rudens"].boxplot(
+        by="Season",
+        ax=ax,
+        grid=False,
+        showfliers=False,
+        boxprops=box_props,
+        medianprops=median_props,
+        whiskerprops=whisker_props,
+        patch_artist=True,
+        widths=width,
+    )
+
+    min_value = np.floor(df_melted["Temperature"].min() / 5) * 5
+    max_value = np.ceil(df_melted["Temperature"].max() / 5) * 5
+    tick_step = 5
+
+    plt.yticks(np.arange(min_value, max_value, tick_step))
     plt.title("Gaisa temperatūra Rīgā četros gadalaikos")
+    plt.suptitle("")
     plt.ylabel("Gaisa temperatūra (Celsija grādos)")
-    # plt.show()
+    plt.xlabel("")
+    plt.show()
 
 
 @logger.catch