initial commit

.gitignore

@@ -0,0 +1 @@
+venv

README.md

@@ -0,0 +1,2 @@
+
+Apple Quality source: https://www.kaggle.com/datasets/nelgiriyewithana/apple-quality/data

cleanup_data.py

@@ -0,0 +1,28 @@
+import pandas as pd
+
+def to_categorical(column, subdivisions):
+    min_value = column.min()
+    max_value = column.max()
+
+    return ((column - min_value) / (max_value - min_value) * subdivisions).round(0)
+
+def normalize_column(column):
+        min_value = min(column)
+        max_value = max(column)
+        return (column-min_value)/(max_value-min_value)
+
+apples = pd.read_csv("apple_quality.csv")
+del apples['A_id']
+apples['Quality'] = apples['Quality'].map({'good':1, 'bad':0})
+
+apples['Juiciness_categorical'] = to_categorical(apples['Juiciness'], 10)
+apples['Ripeness_categorical'] = to_categorical(apples['Ripeness'], 10)
+
+normalized_apples = pd.DataFrame()
+
+for column_name in apples.drop(columns=["Quality"]):
+    normalized_apples[column_name] = normalize_column(apples[column_name])
+
+normalized_apples["Quality"] = apples["Quality"]
+
+normalized_apples.to_csv("apple_quality_clean.csv", index=False)

lab1.py

@@ -0,0 +1,200 @@
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+import numpy as np
+import math
+
+apples = pd.read_csv("apple_quality.csv")
+del apples['A_id']
+apples['Quality'] = apples['Quality'].map({'good':1, 'bad':0})
+
+def to_categorical(column, subdivisions):
+    min_value = column.min()
+    max_value = column.max()
+
+    return ((column - min_value) / (max_value - min_value) * subdivisions).round(0)
+
+apples['Juiciness_categorical'] = to_categorical(apples['Juiciness'], 10)
+apples['Ripeness_categorical'] = to_categorical(apples['Ripeness'], 10)
+
+if False:
+    print("2. Kokybės analizė")
+    for column_name in apples:
+        none_count = (apples[column_name] == None).sum()
+        print(f"{column_name:11}: {none_count} trukstamų reikšmių kiekis")
+
+    print("\n* Kardinalumas")
+    print(apples.drop(columns=["Juiciness_categorical", "Ripeness_categorical", "Quality"]).describe(exclude=['O']))
+
+if False:
+    print("\n3. Kategoriniai")
+    for column_name in ['Quality', 'Juiciness_categorical', 'Ripeness_categorical']:
+        column = apples[column_name]
+        value_counts = column.value_counts()
+        moda = value_counts.index.tolist()[0]
+        moda2 = value_counts.index.tolist()[1]
+
+        moda_count = (column == moda).sum()
+        moda2_count = (column == moda2).sum()
+
+        print(f"* {column_name}")
+        print("  Bendras reikšmių skaičius: ", column.count())
+        print("  Trūkstamų reikšmių procentas: 0%")
+        print("  Kardinalumas: ", len(value_counts))
+        print("  Moda: ", moda)
+        print("  Modos dažnumas: ", moda_count)
+        print("  Modos procentinė reikšmė: ", moda_count / len(apples) * 100)
+        print("  2-Moda: ", moda2)
+        print("  2-Modos dažnumas: ", moda2_count)
+        print("  2-Modos procentinė reikšmė: ", moda2_count / len(apples) * 100)
+
+# 4.
+if False:
+    bin_count = int(1 + 3.22 * math.log(len(apples)))
+    print(bin_count)
+    for column_name in apples:
+        apples[column_name].plot.hist(bins=bin_count)
+        plt.title(column_name)
+        plt.show()
+
+# 7.
+if False:
+    # 7.1.
+    for x_column, y_column in [
+        ("Sweetness", "Size"),
+        ("Sweetness", "Ripeness"),
+        ("Crunchiness", "Ripeness")
+    ]:
+        plt.scatter(apples[x_column], apples[y_column], color='blue', alpha=0.5)
+        plt.xlabel(x_column)
+        plt.ylabel(y_column)
+        plt.title(f'{x_column} vs. {y_column}')
+        plt.grid()
+        plt.show()
+
+    # 7.2.
+    pd.plotting.scatter_matrix(apples.drop(columns=['Quality', 'Juiciness_categorical', 'Ripeness_categorical']), alpha=0.2)
+    plt.show()
+
+    # 7.3.
+    sns.barplot(x='Quality', y='Size', data={
+        "Quality": [
+            0, 1
+        ],
+        "Size": [
+            (apples['Quality'] == 0).sum(),
+            (apples['Quality'] == 1).sum()
+        ]
+    })
+    plt.show()
+
+    bad_apples = apples[apples['Quality'] == 0]
+    good_apples = apples[apples['Quality'] == 1]
+
+    sns.barplot(x='Juiciness', y='Quality', data={
+        "Juiciness": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+        "Quality": [
+            (bad_apples['Juiciness_categorical'] == 0).sum(),
+            (bad_apples['Juiciness_categorical'] == 1).sum(),
+            (bad_apples['Juiciness_categorical'] == 2).sum(),
+            (bad_apples['Juiciness_categorical'] == 3).sum(),
+            (bad_apples['Juiciness_categorical'] == 4).sum(),
+            (bad_apples['Juiciness_categorical'] == 5).sum(),
+            (bad_apples['Juiciness_categorical'] == 6).sum(),
+            (bad_apples['Juiciness_categorical'] == 7).sum(),
+            (bad_apples['Juiciness_categorical'] == 8).sum(),
+            (bad_apples['Juiciness_categorical'] == 9).sum(),
+            (bad_apples['Juiciness_categorical'] == 10).sum(),
+        ]
+    })
+    plt.title("Quality: bad")
+    plt.show()
+
+    sns.barplot(x='Juiciness', y='Quality', data={
+        "Juiciness": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+        "Quality": [
+            (good_apples['Juiciness_categorical'] == 0).sum(),
+            (good_apples['Juiciness_categorical'] == 1).sum(),
+            (good_apples['Juiciness_categorical'] == 2).sum(),
+            (good_apples['Juiciness_categorical'] == 3).sum(),
+            (good_apples['Juiciness_categorical'] == 4).sum(),
+            (good_apples['Juiciness_categorical'] == 5).sum(),
+            (good_apples['Juiciness_categorical'] == 6).sum(),
+            (good_apples['Juiciness_categorical'] == 7).sum(),
+            (good_apples['Juiciness_categorical'] == 8).sum(),
+            (good_apples['Juiciness_categorical'] == 9).sum(),
+            (good_apples['Juiciness_categorical'] == 10).sum(),
+        ]
+    })
+    plt.title("Quality: good")
+    plt.show()
+
+    sns.barplot(x='Ripeness', y='Quality', data={
+        "Ripeness": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+        "Quality": [
+            (bad_apples['Ripeness_categorical'] == 0).sum(),
+            (bad_apples['Ripeness_categorical'] == 1).sum(),
+            (bad_apples['Ripeness_categorical'] == 2).sum(),
+            (bad_apples['Ripeness_categorical'] == 3).sum(),
+            (bad_apples['Ripeness_categorical'] == 4).sum(),
+            (bad_apples['Ripeness_categorical'] == 5).sum(),
+            (bad_apples['Ripeness_categorical'] == 6).sum(),
+            (bad_apples['Ripeness_categorical'] == 7).sum(),
+            (bad_apples['Ripeness_categorical'] == 8).sum(),
+            (bad_apples['Ripeness_categorical'] == 9).sum(),
+            (bad_apples['Ripeness_categorical'] == 10).sum(),
+        ]
+    })
+    plt.title("Quality: bad")
+    plt.show()
+
+    sns.barplot(x='Ripeness', y='Quality', data={
+        "Ripeness": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
+        "Quality": [
+            (good_apples['Ripeness_categorical'] == 0).sum(),
+            (good_apples['Ripeness_categorical'] == 1).sum(),
+            (good_apples['Ripeness_categorical'] == 2).sum(),
+            (good_apples['Ripeness_categorical'] == 3).sum(),
+            (good_apples['Ripeness_categorical'] == 4).sum(),
+            (good_apples['Ripeness_categorical'] == 5).sum(),
+            (good_apples['Ripeness_categorical'] == 6).sum(),
+            (good_apples['Ripeness_categorical'] == 7).sum(),
+            (good_apples['Ripeness_categorical'] == 8).sum(),
+            (good_apples['Ripeness_categorical'] == 9).sum(),
+            (good_apples['Ripeness_categorical'] == 10).sum(),
+        ]
+    })
+    plt.title("Quality: good")
+    plt.show()
+
+    # 7.4.
+    sns.boxplot(apples, x='Quality', y='Juiciness')
+    plt.title("Quality vs Juiciness")
+    plt.show()
+
+    sns.boxplot(apples, x='Quality', y='Ripeness')
+    plt.title("Quality vs Ripeness")
+    plt.show()
+
+# 8.
+if True:
+    #sns.heatmap(apples.drop(columns=["Quality", "Ripeness_categorical", "Juiciness_categorical"]).cov(), annot=True, cmap='coolwarm', fmt=".2f")
+    sns.heatmap(apples.drop(columns=["Quality", "Ripeness_categorical", "Juiciness_categorical"]).corr(), annot=True, cmap='coolwarm', fmt=".2f")
+    plt.show()
+
+# 9.
+if False:
+    def normalize_column(column):
+        min_value = min(column)
+        max_value = max(column)
+        return (column-min_value)/(max_value-min_value)
+
+    normalized_apples = pd.DataFrame()
+
+    for column_name in apples.drop(columns=["Quality"]):
+        normalized_apples[column_name] = normalize_column(apples[column_name])
+
+    normalized_apples["Quality"] = apples["Quality"]
+
+    normalized_apples.to_csv()
+    print(normalized_apples)