💄 Fixes figsize

README.md

@@ -91,6 +91,8 @@ Quite complicated, right? A ton of data packed into one small image, which could
 It can be overwhelming to look at at first, but once you understand what's going on, it's quite intuitive, anyway,
 the function that does all this is also saved in [analyze.py](analyze.py)
 
+All the graphs are saved in the archives, which you can download, [results.tar.gz](results.tar.gz) and [results.zip](results.zip)
+
 ### Neural network
 
 Ah!

analyze.py

@@ -105,7 +105,7 @@ def plot_violin(data, labels, Fs, ps, title):
     grade_name_labels = ["Priemer známok", "Známka z matematiky", "Známka zo slovenčiny", "Známka z angličtiny"]
 
     fig, axs = plt.subplots(2, 2)
-    fig.suptitle(title)
+    fig.suptitle(title, fontsize=18)
     fig.set_size_inches(12, 9)
 
     for j in range(2):
@@ -114,9 +114,9 @@ def plot_violin(data, labels, Fs, ps, title):
             step = 1 if index > 0 else 0.5
 
             parts = axs[j, k].violinplot(data[index], showmedians=True, showmeans=True)
-            axs[j, k].set_title(grade_names[index])
+            axs[j, k].set_title(grade_names[index], fontsize=16)
-            axs[j, k].set_xlabel(title, fontweight="bold")
+            axs[j, k].set_xlabel(title, fontweight="bold", fontsize=14)
-            axs[j, k].set_ylabel(grade_name_labels[index], fontweight="bold")
+            axs[j, k].set_ylabel(grade_name_labels[index], fontweight="bold", fontsize=14)
 
             # q1-q3 lines
             for ind, vec in enumerate(data[index]):
@@ -142,12 +142,14 @@ def plot_violin(data, labels, Fs, ps, title):
             p = ps[index]
             axs[j, k].text(0.01, 0.99, f"F-stat: {F:.4f}\np-val: {p:.4f}", ha="left", va="top",
                            transform=axs[j, k].transAxes,
-                           fontweight="bold")
+                           fontweight="bold",
+                           fontsize=12)
             axs[j, k].text(0.99, 0.99,
                            f"Na ľavo - priemer (červená)\nNa pravo - medián (zelená)\nSivá - medzi kvartilom 1 a 3",
                            ha="right",
                            va="top",
-                           transform=axs[j, k].transAxes)
+                           transform=axs[j, k].transAxes,
+                           fontsize=12)
 
             medians = list([np.median(a) for a in data[index]])
             means = list([a.mean() for a in data[index]])
@@ -155,8 +157,8 @@ def plot_violin(data, labels, Fs, ps, title):
                 median = medians[l]
                 mean = means[l]
                 # left - mean, right - median
-                axs[j, k].text(l + 1.13, median - 0.05, f"{median:.2f}", color="green")
+                axs[j, k].text(l + 1.13, median - 0.05, f"{median:.2f}", color="green", fontsize=12, fontweight="bold")
-                axs[j, k].text(l + 0.90 - len(labels) * 0.065, mean - 0.05, f"{mean:.2f}", color="red")
+                axs[j, k].text(l + 0.87 - len(labels) * 0.065, mean - 0.05, f"{mean:.2f}", color="red", fontsize=12, fontweight="bold")
 
     fig.tight_layout()
     if save != "":

analyze_absence.py

@@ -49,7 +49,7 @@ grade_names = ["Priemer", "Matematika", "Slovenčina", "Angličtina"]
 grade_name_labels = ["Priemer známok", "Známka z matematiky", "Známka zo slovenčiny", "Známka z angličtiny"]
 
 fig, axs = plt.subplots(2, 2)
-fig.suptitle("Absencia")
+fig.suptitle("Absencia", fontsize=18)
 fig.set_size_inches(12, 9)
 
 for j in range(2):
@@ -61,8 +61,8 @@ for j in range(2):
             x = data[index][0]  # absence
             y = data[index][1]  # grade
             axs[j, k].scatter(x, y)
-            axs[j, k].set_xlabel("Počet vymeškaných hodín")
+            axs[j, k].set_xlabel("Počet vymeškaných hodín", fontweight="bold", fontsize=14)
-            axs[j, k].set_ylabel(grade_name_labels[index])
+            axs[j, k].set_ylabel(grade_name_labels[index], fontweight="bold", fontsize=14)
             axs[j, k].set_yticks(np.arange(1, 6))
 
             # trendline
@@ -76,15 +76,18 @@ for j in range(2):
             # data[index][1] - grades
             # data[index][0][specific grade] - absences for that specific grande
             # loop 1 through 5 plug in ^^
+            axs[j, k].set_xlabel(grade_name_labels[index], fontweight="bold", fontsize=14)
+            axs[j, k].set_ylabel("Počet vymeškaných hodín", fontweight="bold", fontsize=14)
             axs[j, k].boxplot(by_grade, tick_labels=["1", "2", "3", "4", "5"])
 
-        axs[j, k].set_title(grade_names[index])
+        axs[j, k].set_title(grade_names[index], fontsize=16)
 
         tau = taus[index]
         p = ps[index]
         axs[j, k].text(0.01, 0.99, f"Tau τ: {tau:.4f}\np-val: {p:.4f}", ha="left", va="top",
                        transform=axs[j, k].transAxes,
-                       fontweight="bold")
+                       fontweight="bold",
+                       fontsize=12)
 
 fig.tight_layout()
 if save != "":

distribution.py

@@ -35,8 +35,8 @@ def plot_pie(data, labels, title, explode=None):
             i += 1
 
     plt.figure(figsize=(8, 6))
-    plt.pie(np.array(data), labels=labels, autopct=lambda pct: percent(pct / 100), explode=explode)
+    plt.pie(np.array(data), labels=labels, autopct=lambda pct: percent(pct / 100), explode=explode, textprops={"fontsize": 16})
-    plt.title(title)
+    plt.title(title, fontsize=20)
 
     plt.tight_layout()
     if save:
@@ -53,9 +53,9 @@ def plot_hist(data, title, xlabel, ylabel):
 
     plt.figure(figsize=(8, 6))
     plt.hist(data, 25, edgecolor="black")
-    plt.title(title)
+    plt.title(title, fontsize=20)
-    plt.xlabel(xlabel)
+    plt.xlabel(xlabel, fontsize=16)
-    plt.ylabel(ylabel)
+    plt.ylabel(ylabel, fontsize=16)
 
     plt.tight_layout()
     if save:
@@ -103,7 +103,7 @@ print("--- GPA ---")
 print("n/a")
 print("")
 
-plot_hist(dataset[:, 2], "Distribúcia piemernu známok", "Piemerná známka", "Počet študentov/tiek")
+plot_hist(dataset[:, 2], "Distribúcia piemernu známok", "Piemerná známka", "Počet študent*iek")
 
 math = dataset[:, 3]
 math_dist = [
@@ -192,7 +192,7 @@ print(f"none                   : {percent(occupation_dist[5])}")
 print("")
 
 plot_pie(occupation_dist,
-         ["Práca 10 a viac hodín týždenne", "Práca menej ako 10 hodín týždenne", "Šport", "Hudba", "Niečo iné",
+         ["Práca 10 a viac\nhodín týždenne", "Práca menej ako\n10 hodín týždenne", "Šport", "Hudba", "Niečo iné",
           "Žiadne"], "Distribúcia práce a aktivít")
 
 living = dataset[:, 8]
@@ -212,7 +212,7 @@ print(f"other             : {percent(living_dist[4])}")
 print("")
 
 plot_pie(living_dist,
-         ["S rodinou", "S rodinným príslušníkom/ou", "Sám/a alebo so spolubývajúcim/ou", "Intrák", "Iné"],
+         ["S rodinou", "\nS rodinnou príslušní*čkou", "Sám*a alebo so\nspolubývajúc*ou", "Intrák", "Iné"],
          "Distribúcia životných situácií")
 
 commute = dataset[:, 9]
@@ -253,4 +253,4 @@ print("--- ABSENCE ---")
 print("n/a")
 print("")
 
-plot_hist(dataset[:, 11], "Distribúcia absencií", "Počet neprítomných hodín", "Počet študentov/tiek")
+plot_hist(dataset[:, 11], "Distribúcia absencií", "Počet neprítomných hodín", "Počet študent*iek")

requirements.txt

@@ -1,47 +1,9 @@
-contourpy==1.3.1
+numpy
-cycler==0.12.1
+matplotlib
-filelock==3.16.1
+PyQt6
-fonttools==4.55.3
+pandas
-fsspec==2024.12.0
+scipy
-Jinja2==3.1.5
+scikit_posthocs
-joblib==1.4.2
+tabulate
-kiwisolver==1.4.7
+torch
-MarkupSafe==3.0.2
+scikit-learn
-matplotlib==3.10.0
-mpmath==1.3.0
-networkx==3.4.2
-numpy==2.2.1
-nvidia-cublas-cu12==12.4.5.8
-nvidia-cuda-cupti-cu12==12.4.127
-nvidia-cuda-nvrtc-cu12==12.4.127
-nvidia-cuda-runtime-cu12==12.4.127
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.2.1.3
-nvidia-curand-cu12==10.3.5.147
-nvidia-cusolver-cu12==11.6.1.9
-nvidia-cusparse-cu12==12.3.1.170
-nvidia-nccl-cu12==2.21.5
-nvidia-nvjitlink-cu12==12.4.127
-nvidia-nvtx-cu12==12.4.127
-packaging==24.2
-pandas==2.2.3
-pandas-flavor==0.6.0
-patsy==1.0.1
-pillow==11.0.0
-pyparsing==3.2.0
-python-dateutil==2.9.0.post0
-pytz==2024.2
-scikit-learn==1.6.0
-scikit-posthocs==0.11.2
-scipy==1.14.1
-seaborn==0.13.2
-setuptools==75.6.0
-six==1.17.0
-statsmodels==0.14.4
-sympy==1.13.1
-tabulate==0.9.0
-threadpoolctl==3.5.0
-torch==2.5.1
-typing_extensions==4.12.2
-tzdata==2024.2
-xarray==2024.11.0