zad 1

zad1/README.txt

@@ -0,0 +1,15 @@
+CHARAKTERYSTYKA GATUNKÓW IRYSÓW
+
+Liczba klas (gatunków): 3
+
+Liczba obserwacji: 150 (50 dla każdego gatunku)
+
+Atrybuty (kolumny):
+1. długość działki kielicha (ang. sepal length) [cm]
+2. szerokość działki kielicha (ang. sepal width) [cm]
+3. długość płatka (ang. petal length) [cm]
+4. szerokość płatka (ang. petal width) [cm]
+5. gatunek (ang. species):
+   0 - setosa
+   1 - versicolor
+   2 - virginica

zad1/data.csv

@@ -0,0 +1,150 @@
+5.1,3.5,1.4,0.2,0
+4.9,3.0,1.4,0.2,0
+4.7,3.2,1.3,0.2,0
+4.6,3.1,1.5,0.2,0
+5.0,3.6,1.4,0.2,0
+5.4,3.9,1.7,0.4,0
+4.6,3.4,1.4,0.3,0
+5.0,3.4,1.5,0.2,0
+4.4,2.9,1.4,0.2,0
+4.9,3.1,1.5,0.1,0
+5.4,3.7,1.5,0.2,0
+4.8,3.4,1.6,0.2,0
+4.8,3.0,1.4,0.1,0
+4.3,3.0,1.1,0.1,0
+5.8,4.0,1.2,0.2,0
+5.7,4.4,1.5,0.4,0
+5.4,3.9,1.3,0.4,0
+5.1,3.5,1.4,0.3,0
+5.7,3.8,1.7,0.3,0
+5.1,3.8,1.5,0.3,0
+5.4,3.4,1.7,0.2,0
+5.1,3.7,1.5,0.4,0
+4.6,3.6,1.0,0.2,0
+5.1,3.3,1.7,0.5,0
+4.8,3.4,1.9,0.2,0
+5.0,3.0,1.6,0.2,0
+5.0,3.4,1.6,0.4,0
+5.2,3.5,1.5,0.2,0
+5.2,3.4,1.4,0.2,0
+4.7,3.2,1.6,0.2,0
+4.8,3.1,1.6,0.2,0
+5.4,3.4,1.5,0.4,0
+5.2,4.1,1.5,0.1,0
+5.5,4.2,1.4,0.2,0
+4.9,3.1,1.5,0.2,0
+5.0,3.2,1.2,0.2,0
+5.5,3.5,1.3,0.2,0
+4.9,3.6,1.4,0.1,0
+4.4,3.0,1.3,0.2,0
+5.1,3.4,1.5,0.2,0
+5.0,3.5,1.3,0.3,0
+4.5,2.3,1.3,0.3,0
+4.4,3.2,1.3,0.2,0
+5.0,3.5,1.6,0.6,0
+5.1,3.8,1.9,0.4,0
+4.8,3.0,1.4,0.3,0
+5.1,3.8,1.6,0.2,0
+4.6,3.2,1.4,0.2,0
+5.3,3.7,1.5,0.2,0
+5.0,3.3,1.4,0.2,0
+7.0,3.2,4.7,1.4,1
+6.4,3.2,4.5,1.5,1
+6.9,3.1,4.9,1.5,1
+5.5,2.3,4.0,1.3,1
+6.5,2.8,4.6,1.5,1
+5.7,2.8,4.5,1.3,1
+6.3,3.3,4.7,1.6,1
+4.9,2.4,3.3,1.0,1
+6.6,2.9,4.6,1.3,1
+5.2,2.7,3.9,1.4,1
+5.0,2.0,3.5,1.0,1
+5.9,3.0,4.2,1.5,1
+6.0,2.2,4.0,1.0,1
+6.1,2.9,4.7,1.4,1
+5.6,2.9,3.6,1.3,1
+6.7,3.1,4.4,1.4,1
+5.6,3.0,4.5,1.5,1
+5.8,2.7,4.1,1.0,1
+6.2,2.2,4.5,1.5,1
+5.6,2.5,3.9,1.1,1
+5.9,3.2,4.8,1.8,1
+6.1,2.8,4.0,1.3,1
+6.3,2.5,4.9,1.5,1
+6.1,2.8,4.7,1.2,1
+6.4,2.9,4.3,1.3,1
+6.6,3.0,4.4,1.4,1
+6.8,2.8,4.8,1.4,1
+6.7,3.0,5.0,1.7,1
+6.0,2.9,4.5,1.5,1
+5.7,2.6,3.5,1.0,1
+5.5,2.4,3.8,1.1,1
+5.5,2.4,3.7,1.0,1
+5.8,2.7,3.9,1.2,1
+6.0,2.7,5.1,1.6,1
+5.4,3.0,4.5,1.5,1
+6.0,3.4,4.5,1.6,1
+6.7,3.1,4.7,1.5,1
+6.3,2.3,4.4,1.3,1
+5.6,3.0,4.1,1.3,1
+5.5,2.5,4.0,1.3,1
+5.5,2.6,4.4,1.2,1
+6.1,3.0,4.6,1.4,1
+5.8,2.6,4.0,1.2,1
+5.0,2.3,3.3,1.0,1
+5.6,2.7,4.2,1.3,1
+5.7,3.0,4.2,1.2,1
+5.7,2.9,4.2,1.3,1
+6.2,2.9,4.3,1.3,1
+5.1,2.5,3.0,1.1,1
+5.7,2.8,4.1,1.3,1
+6.3,3.3,6.0,2.5,2
+5.8,2.7,5.1,1.9,2
+7.1,3.0,5.9,2.1,2
+6.3,2.9,5.6,1.8,2
+6.5,3.0,5.8,2.2,2
+7.6,3.0,6.6,2.1,2
+4.9,2.5,4.5,1.7,2
+7.3,2.9,6.3,1.8,2
+6.7,2.5,5.8,1.8,2
+7.2,3.6,6.1,2.5,2
+6.5,3.2,5.1,2.0,2
+6.4,2.7,5.3,1.9,2
+6.8,3.0,5.5,2.1,2
+5.7,2.5,5.0,2.0,2
+5.8,2.8,5.1,2.4,2
+6.4,3.2,5.3,2.3,2
+6.5,3.0,5.5,1.8,2
+7.7,3.8,6.7,2.2,2
+7.7,2.6,6.9,2.3,2
+6.0,2.2,5.0,1.5,2
+6.9,3.2,5.7,2.3,2
+5.6,2.8,4.9,2.0,2
+7.7,2.8,6.7,2.0,2
+6.3,2.7,4.9,1.8,2
+6.7,3.3,5.7,2.1,2
+7.2,3.2,6.0,1.8,2
+6.2,2.8,4.8,1.8,2
+6.1,3.0,4.9,1.8,2
+6.4,2.8,5.6,2.1,2
+7.2,3.0,5.8,1.6,2
+7.4,2.8,6.1,1.9,2
+7.9,3.8,6.4,2.0,2
+6.4,2.8,5.6,2.2,2
+6.3,2.8,5.1,1.5,2
+6.1,2.6,5.6,1.4,2
+7.7,3.0,6.1,2.3,2
+6.3,3.4,5.6,2.4,2
+6.4,3.1,5.5,1.8,2
+6.0,3.0,4.8,1.8,2
+6.9,3.1,5.4,2.1,2
+6.7,3.1,5.6,2.4,2
+6.9,3.1,5.1,2.3,2
+5.8,2.7,5.1,1.9,2
+6.8,3.2,5.9,2.3,2
+6.7,3.3,5.7,2.5,2
+6.7,3.0,5.2,2.3,2
+6.3,2.5,5.0,1.9,2
+6.5,3.0,5.2,2.0,2
+6.2,3.4,5.4,2.3,2
+5.9,3.0,5.1,1.8,2

zad1/main.py

@@ -0,0 +1,207 @@
+"""
+Komputerowa analiza danych
+Zadanie 1
+Michał Leśniak 195642
+"""
+import math
+import locale
+locale.setlocale(locale.LC_ALL, '')
+
+SPECIES_NAMES = {
+    '0': 'setosa',
+    '1': 'versicolor',
+    '2': 'virginica'
+}
+
+ATTRIBUTE_NAMES = ['Długość działki kielicha [cm]',
+                   'Szerokość działki kielicha [cm]',
+                   'Długość płatka [cm]',
+                   'Szerokość płatka [cm]']
+
+
+def mean(lst):
+    sum = 0
+    for i in lst:
+        sum += i
+    return sum/len(lst)
+
+
+def median(lst, is_even):
+    return (lst[len(lst)//2-1]+lst[len(lst)//2])/2 if is_even else lst[len(lst)//2]
+
+
+def sample_standard_deviation(lst, lst_mean):
+    sum = 0
+    for x in [(y-lst_mean)**2 for y in lst]:
+        sum += x
+    return math.sqrt(sum/(len(lst)-1))
+
+
+def q1(lst, is_even, lst_median):
+    idx = len(lst)//2-1 if is_even else len(lst)//2+1
+    sorted_list = lst[:idx]
+    if is_even:
+        sorted_list.append(lst_median)
+
+    return median(sorted_list, is_even)
+
+
+def q3(lst, is_even, lst_median):
+    idx = len(lst)//2+1 if is_even else len(lst)//2
+    sorted_list = lst[idx:]
+    if is_even:
+        sorted_list.insert(0, lst_median)
+
+    return median(sorted_list, is_even)
+
+
+def min(lst):
+    return lst[0]
+
+
+def max(lst):
+    return lst[-1]
+
+
+def calc_data(lst):
+    is_even = len(lst) % 2 == 0
+    lst_mean = mean(lst)
+    lst_median = median(lst, is_even)
+    return min(lst), lst_mean, sample_standard_deviation(lst, lst_mean), lst_median, q1(lst, is_even, lst_median), q3(lst, is_even, lst_median), max(lst)
+
+
+def calc_species_data(species):
+    total = 0
+    for x in species.values():
+        total += x
+
+    species_list = []
+    for key in species:
+        species_list.append(
+            (SPECIES_NAMES[key], species[key], species[key]/total))
+
+    species_list.append(("Razem", total, 1.0))
+
+    return species_list
+
+
+def percentage_format(x):
+    return locale.format_string('%.1f%%', x*100)
+
+
+def float_format(x):
+    return locale.format_string('%.2f', x)
+
+
+def print_table(table):
+    if not table:
+        return
+    cell_sizes = [0] * len(table[0])
+    for i in range(len(table[0])):
+        for x in table:
+            if not x:
+                continue
+            if len(x[i]) > cell_sizes[i]:
+                cell_sizes[i] = len(x[i])
+
+    header_row_format = ' | '.join((f'{{:^{x}}}' for x in cell_sizes))
+    row_format = f'{{:<{cell_sizes[0]}}} | ' + \
+        ' | '.join((f'{{:^{x}}}' for x in cell_sizes[1:]))
+
+    lines = []
+    for x in table:
+        if x == table[0]:
+            lines.append(header_row_format.format(*x))
+            continue
+        if x is None:
+            lines.append(None)
+            continue
+        lines.append(row_format.format(*x))
+    row_size = 0
+    for x in lines:
+        if x and len(x) > row_size:
+            row_size = len(x)
+    row_size += 1
+    lines.insert(1, '='*row_size)
+    lines.insert(0, '='*row_size)
+    lines.insert(len(lines), '='*row_size)
+    for i in range(len(lines)):
+        if lines[i] is None:
+            lines[i] = '-'*row_size
+    for x in lines:
+        print(x)
+
+
+def print_data(species_data, trait_data):
+    species_printable_table = []
+    species_printable_table.append(("Gatunek", "Liczebność (%)"))
+    for x in species_data:
+        if x == species_data[-1]:
+            species_printable_table.append(None)
+        species_printable_table.append(
+            (x[0], "{} ({})".format(x[1], percentage_format(x[2]))))
+
+    trait_printable_table = []
+    trait_printable_table.append(
+        ("Cecha", "Minimum", "Śr. arytm. (± odch. stand.)", "Mediana (Q1 - Q3)", "Maksimum"))
+    for i in range(len(trait_data)):
+        trait_printable_table.append((ATTRIBUTE_NAMES[i],
+                                      float_format(trait_data[i][0]),
+                                      "{} (±{})".format(float_format(
+                                          trait_data[i][1]), float_format(trait_data[i][2])),
+                                      "{} ({} - {})".format(
+                                          float_format(trait_data[i][3]),
+                                          float_format(trait_data[i][4]),
+                                          float_format(trait_data[i][5])),
+                                      float_format(trait_data[i][6])))
+
+    print_table(species_printable_table)
+    print()
+    print_table(trait_printable_table)
+
+
+def main():
+    # read data
+    with open("data.csv", "r") as f:
+        data = f.read().splitlines()
+
+    # parse data
+    sepal_length_list = []
+    sepal_width_list = []
+    petal_length_list = []
+    petal_width_list = []
+    species_dict = {
+        '0': 0,
+        '1': 0,
+        '2': 0,
+    }
+    for line in data:
+        sepal_length, sepal_width, petal_length, petal_width, species = line.split(
+            ',')
+        sepal_length_list.append(float(sepal_length))
+        sepal_width_list.append(float(sepal_width))
+        petal_length_list.append(float(petal_length))
+        petal_width_list.append(float(petal_width))
+        species_dict[species] += 1
+
+    sepal_length_list.sort()
+    sepal_width_list.sort()
+    petal_length_list.sort()
+    petal_width_list.sort()
+
+    # calculate results
+    species_data = calc_species_data(species_dict)
+
+    trait_data = []
+
+    for lst in [sepal_length_list, sepal_width_list, petal_length_list, petal_width_list]:
+        trait_data.append(calc_data(lst))
+
+    # print results
+    print_data(species_data, trait_data)
+
+
+if __name__ == "__main__":
+    import os.path
+    assert os.path.isfile('data.csv')
+    main()