Add assignment 5 content

assignments/A5/.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

assignments/A5/.idea/A5.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

assignments/A5/.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

assignments/A5/.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (python-venv)" project-jdk-type="Python SDK" />
+</project>

assignments/A5/.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/A5.iml" filepath="$PROJECT_DIR$/.idea/A5.iml" />
+    </modules>
+  </component>
+</project>

assignments/A5/.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$/../.." vcs="Git" />
+  </component>
+</project>

assignments/A5/readcsv.py

@@ -0,0 +1,121 @@
+def read_csv(filename):
+    """Read a CSV file, return list of rows"""
+
+    import csv
+    with open(filename, 'rt', newline='') as f:
+        reader = csv.reader(f, skipinitialspace=True)
+        return [row for row in reader]
+
+
+def header_map(headers):
+    """
+    Read a list, and convert it to a dictionary where the key is each element of the given list and the value is
+    its position in the list
+    :param headers: List
+    :return: Dict
+    """
+
+    header_dict = dict()
+    i = 0
+    for header in headers:
+        header_dict[header] = i
+        i = i + 1
+    return header_dict
+
+
+def select(table, search_items):
+    """
+    Read the set in the second argument and search through the table in the first argument and return the
+    columns that match the query in the search items
+    :param table: List
+    :param search_items: List
+    :return: List
+    """
+
+    header_numbers = header_map(table[0])
+    ret_list = list()
+    columns = list()
+
+    for item in search_items:
+        columns.append(header_numbers[item])
+    columns.sort()
+    for item in table:
+        lst = list()
+        for number in columns:
+            lst.append(item[number])
+        ret_list.append(lst)
+    return ret_list
+
+
+def row2dict(hmap, row):
+    """
+    Convert a row in the second argument, given the headers in the first argument to a dictionary which uses the
+    headers as keys and the row data as values
+    :param hmap: Dictionary
+    :param row: List
+    :return: Dictionary
+    """
+    ret_dict = dict()
+    for key in hmap:
+        ret_dict[key] = row[hmap[key]]
+    return ret_dict
+
+
+def check_row(row, query):
+    """
+    Check the row in the first argument passes a query in the second argument. The second argument is a formatted
+    tuple where the first element in the tuple is a column name, the second is an operation (==, <=, >=, AND,
+    OR) and the third element is a condition, numeric or string matching. (ex: is age == 34, is color == blue). AND
+    and OR are special in that you can pass in recursive tuples (left and right argument are tuples) that will also
+    be evaluated recursively
+    :param row: List
+    :param query: Tuple
+    :return: Boolean
+    """
+
+    def perform_operation(op, var, cond):
+        if type(var) is str:
+            if var.isnumeric():
+                var = int(var)
+        if type(cond) is str:
+            if cond.isnumeric():
+                cond = int(cond)
+
+        if op == '==':
+            return var == cond
+        elif op == '>=':
+            return var >= cond
+        elif op == '<=':
+            return var <= cond
+        elif op == 'OR':
+            return perform_operation(var[1], row[var[0]], var[2]) or perform_operation(cond[1], row[cond[0]], cond[2])
+        elif op == 'AND':
+            return perform_operation(var[1], row[var[0]], var[2]) and perform_operation(cond[1], row[cond[0]], cond[2])
+        else:
+            return False
+
+    if type(query[0]) and type(query[2]) is tuple:
+        return perform_operation(query[1], query[0], query[2])
+    elif query[2] not in row:
+        stringify = str(query[2])
+        return perform_operation(query[1], row[str(query[0])], stringify)
+    else:
+        return perform_operation(query[1], row[str(query[0])], row[query[2]])
+
+
+def filter_table(table, query):
+    """
+    This function takes a table of csv values, and performs the query to filter out the rows that do not match the query
+    :param table: List
+    :param query: Tuple
+    :return: List
+    """
+    header_row = header_map(table[0])
+    data_rows = table[1:]
+    result = list()
+    result.append(table[0])
+    for row in data_rows:
+        data_dict = row2dict(header_row, row)
+        if check_row(data_dict, query):
+            result.append(row)
+    return result

assignments/A5/test1.csv

@@ -0,0 +1,4 @@
+name,   age,    eye colour
+Bob,    5,      blue
+Mary,   27,     brown
+Vij,    54,     green

assignments/A5/test2.csv

@@ -0,0 +1,3 @@
+name, 100
+teddy, 500
+lovely, 1000

assignments/A5/test_readcsv.py

@@ -0,0 +1,93 @@
+from readcsv import read_csv
+from readcsv import header_map
+from readcsv import select
+from readcsv import row2dict
+from readcsv import check_row
+from readcsv import filter_table
+
+table = read_csv('test1.csv')
+sampledata = read_csv('2014-1000.csv')
+
+
+def test_read_csv():
+    assert read_csv('test1.csv') == [['name', 'age', 'eye colour'],
+                                     ['Bob', '5', 'blue'],
+                                     ['Mary', '27', 'brown'],
+                                     ['Vij', '54', 'green']]
+
+
+def test_header_map_1():
+    hmap = header_map(table[0])
+    assert hmap == {'name': 0, 'age': 1, 'eye colour': 2}
+
+
+def test_select_1():
+    assert select(table, {'name', 'eye colour'}) == [['name', 'eye colour'],
+                                                     ['Bob', 'blue'],
+                                                     ['Mary', 'brown'],
+                                                     ['Vij', 'green']]
+
+
+def test_row2dict():
+    hmap = header_map(table[0])
+    assert row2dict(hmap, table[1]) == {'name': 'Bob', 'age': '5', 'eye colour': 'blue'}
+
+
+def test_check_row():
+    row = {'name': 'Bob', 'age': '5', 'eye colour': 'blue'}
+    assert check_row(row, ('age', '==', 5))
+    assert not check_row(row, ('eye colour', '==', 5))
+    assert check_row(row, ('eye colour', '==', 'blue'))
+    assert check_row(row, ('age', '>=', 4))
+    assert check_row(row, ('age', '<=', 1000))
+
+
+def test_check_row_logical():
+    row = {'name': 'Bob', 'age': '5', 'eye colour': 'blue'}
+    assert check_row(row, (('age', '==', 5), 'OR', ('eye colour', '==', 5)))
+    assert not check_row(row, (('age', '==', 5), 'AND', ('eye colour', '==', 5)))
+
+
+def test_filter_table1():
+    assert filter_table(table, ('age', '>=', 0)) == [['name', 'age', 'eye colour'],
+                                                     ['Bob', '5', 'blue'],
+                                                     ['Mary', '27', 'brown'],
+                                                     ['Vij', '54', 'green']]
+
+    assert filter_table(table, ('age', '<=', 27)) == [['name', 'age', 'eye colour'],
+                                                      ['Bob', '5', 'blue'],
+                                                      ['Mary', '27', 'brown']]
+
+    assert filter_table(table, ('eye colour', '==', 'brown')) == [['name', 'age', 'eye colour'],
+                                                                  ['Mary', '27', 'brown']]
+
+    assert filter_table(table, ('name', '==', 'Vij')) == [['name', 'age', 'eye colour'],
+                                                          ['Vij', '54', 'green']]
+
+
+def test_filter_table2():
+    assert filter_table(table, (('age', '>=', 0), 'AND', ('age', '>=', '27'))) == [['name', 'age', 'eye colour'],
+                                                                                   ['Mary', '27', 'brown'],
+                                                                                   ['Vij', '54', 'green']]
+
+    assert filter_table(table, (('age', '<=', 27), 'AND', ('age', '>=', '27'))) == [['name', 'age', 'eye colour'],
+                                                                                    ['Mary', '27', 'brown']]
+
+    assert filter_table(table, (('eye colour', '==', 'brown'),
+                                'OR',
+                                ('name', '==', 'Vij'))) == [['name', 'age', 'eye colour'],
+                                                            ['Mary', '27', 'brown'],
+                                                            ['Vij', '54', 'green']]
+
+
+# Student Tests
+
+def test_check_row_2():
+    row = {'name': 'Bob', 'age': '5', 'eye colour': 'blue'}
+    assert not check_row(row, ('age', '===', 5))
+
+
+def test_check_row_3():
+    # Could not get test to pass, but included for completeness of tests
+    table2 = read_csv('test2.csv')
+    assert check_row(table2[1], ("100", "==", "500"))