Group 1

tasks/collections1.py

@@ -1,14 +1,19 @@
+""" 
+Group 1. Collaboration with Klara, Marije, Sarab.
 
+"""
+
+import collections
 
 def get_word_counts(docs):
 
-    """
-    use the Collections python standard librar to count the words in the documents
-    docs = [[w1,w2], [w4,w2,w3,w1] ....]
+	"""
+	use the Collections python standard librar to count the words in the documents
+	docs = [[w1,w2], [w4,w2,w3,w1] ....]
 
-    restrictions:
-    1) you have to use Collections
-    2) you have 4 lines of code, including return statement
-    """
-    pass
+	restrictions:
+	1) you have to use Collections
+	2) you have 4 lines of code, including return statement
+	"""
 
+	return collections.Counter([w for doc in docs for w in doc])

tasks/data_generator.py

@@ -1,15 +1,16 @@
 
+"""
 
+Group 1. Collaboration with Klara, Marije, Sarab.
 
-"""
 create a class that given a list of text files will at each iteration return
 the first line of the text only if the file is not suppose to be ignored (see example files below)
 
 example:
 
 lets assume we have the following files and that the first line of each file is the name of the file
 
-files = ["file1.txt", "file2.txt", "ingore_this_file1.txt", "file3.txt", "ingore_this_file1.txt", "file4.txt"]
+files = ["file1.txt", "file2.txt", "ignore_this_file1.txt", "file3.txt", "ignore_this_file1.txt", "file4.txt"]
 
 
 following code should run:
@@ -27,5 +28,42 @@
 
 """
 
+
 class DataGenerator:
-    pass
+
+	def __init__(self, data):
+		self.data = data
+		self.current = 0
+		self.end = len(self.data)
+
+	def __iter__(self):
+		for filename in self.data:
+			with open(filename) as f:
+				first_line = f.readline()  # reads only the first line of the file
+				if "ignore" not in first_line:  # only the files that should not be ignored
+					self.current +=1
+					yield first_line  # gives back the first line of the file
+				else:
+					self.current += 1
+
+	def __next__(self):
+		if self.current == self.end:
+			raise StopIteration  # stops the iteration when there are no files left
+		else:
+			if "ignore" in self.data[self.current]:
+				self.current += 1
+				return next(self)  # if the current file should be ignored it continues to the next one
+			else:
+				filename = self.data[self.current]
+				with open(filename) as f:
+					first_line = f.readline()
+					return first_line
+
+if __name__ == '__main__':
+	files = ["file1.txt", "file2.txt", "ignore_this_file1.txt", "file3.txt", "ignore_this_file2.txt", "file4.txt"]
+	my_generator = DataGenerator(files)
+	for data in my_generator:
+		print(data)
+		if "3" in data:  # tests to see if files with ignore are ignored until you reach file3
+			break
+	print(next(my_generator))

tasks/dict_comp1.py

@@ -1,13 +1,20 @@
+""" 
+Group 1. Collaboration with Klara, Marije, Sarab.
 
+"""
 
 
 def merge_dicts(dict1,dict2,dict3):
     """
     Change the for loop to a one line dict comprehension
     """
-
-    new_dict = {}
-    for d in [dict1,dict2,dict3]:
-        new_dict.update(d)
+
+    new_dict = {k: v for d in [dict1,dict2,dict3] for k, v in d.items()}
 
-    return new_dict
+    return new_dict
+
+if __name__ == "__main__":
+    dict1 = {'1':1, '2':2, '3':3}
+    dict2 = {'a':'a', 'b':'b', 'c':'c'}
+    dict3 = {'w':'w', 'z':'z', 'y':'y'}
+    print(merge_dicts(dict1,dict2,dict3))

tasks/recursion1.py

@@ -1,12 +1,11 @@
+import json
 
 
-
-def construct_trees(nodes:list):
-
+def construct_trees(nodes: list):
     """
-    given the following list where the first item in the tuple is the node_id and 
+    given the following list where the first item in the tuple is the node_id and
     the second item is the node_id of the parent; (NODE_ID, PARENT_NODE_ID)
-    
+
     nodes = [
                 ("node1", "node1"),
                 ("node2", "node1"),
@@ -26,7 +25,7 @@ def construct_trees(nodes:list):
                     "node2": {
                                 "node4":
                                         {
-                                        
+
                                         }
                                 },
                     "node5": {},
@@ -43,24 +42,56 @@ def construct_trees(nodes:list):
                                 }
 
                     }
- 
+
         }
 
     Restrictions
     1) place_node() should be a recusive function
-    
+
     Tips!
         - let construct_trees() run until all nodes are places, or until there are no more
         nodes to place!
         - you might need a special condition to deal with the root of trees, e.g, nodes that have themselves as parents.
 
     """
 
-    def place_node():
-        #FIX THIS FUCNTION
-
-
-    #FIX THIS FUCNTION
-    pass
-
+    """
+    Group 1. Collaboration with Klara, Marije, Sarab.
+    """
+
+    def place_node(d: dict, node):
+        node_id, parent_id = node
+        if node_id == parent_id:  # checks if this is a root
+            d[parent_id] = {}  # place root nodes
+            return True
+        elif parent_id in d.keys():  # checks if parent node is already in the tree/subtrees
+            d[parent_id][node_id] = {}  # places the nodes in the correct place
+            return True
+        for k in d:
+            # checks all the keys of the subtree until parent_id is found
+            if place_node(d[k], node):
+                return True
+        return False
+
+    trees = {}
+    while len(nodes) > 0:
+        node = nodes.pop(0)
+        if not place_node(trees, node):  # checks if it is possible to place node now
+            nodes.append(node)  # puts back nodes that weren't placed yet
+    return trees
+
+
+if __name__ == '__main__':
+    nodes = [
+        ("node1", "node1"),
+        ("node2", "node1"),
+        ("node3", "node8"),
+        ("node4", "node2"),
+        ("node5", "node1"),
+        ("node6", "node7"),
+        ("node7", "node7"),
+        ("node8", "node9"),
+        ("node9", "node6"),
+    ]
 
+    print(json.dumps(construct_trees(nodes), indent=12, sort_keys=True))