datacamp creating robust workflows

Author: ptyadana

Data Science with Python - DataCamp/11.Creating Robust Workflows in Python/01.Principles.pdf

@@ -0,0 +1,42 @@
+from pathlib import Path
+
+def print_files(filenames):
+    # Set up the loop iteration instructions
+    for name in filenames:
+        # Use pathlib.Path to print out each file
+        print(Path(name).read_text())
+        
+def list_files(filenames):
+    # Use pathlib.Path to read the contents of each file
+    return [Path(name).read_text()
+            # Obtain each name from the list of filenames
+            for name in filenames]
+
+filenames = "diabetes.txt", "boston.txt", "digits.txt", "iris.txt", "wine.txt"
+print_files(filenames)
+pprint(list_files(filenames))
+
+
+def get_matches(filename, query):
+    # Filter the list comprehension using an if clause
+    return [line for line in Path(filename).open() if query in line]
+
+# Iterate over files to find all matching lines
+matches = [get_matches(name, "Number of") for name in filenames]
+pprint(matches)
+
+
+def flatten(nested_list):
+    return (item 
+            # Obtain each list from the list of lists
+            for sublist in nested_list
+            # Obtain each element from each individual list
+            for item in sublist)
+
+number_generator = (int(substring) for string in flatten(matches)
+                    for substring in string.split() if substring.isdigit())
+
+pprint(dict(zip(filenames, zip(number_generator, number_generator))))
+
+
+

Data Science with Python - DataCamp/11.Creating Robust Workflows in Python/02.Documentation and Tests.pdf

@@ -0,0 +1,13 @@
+from pathlib import Path
+
+def obtain_words(string):
+    # Replace non-alphabetic characters with spaces
+    return "".join(char if char.isalpha() else " " for char in string).split()
+
+def filter_words(words, minimum_length=3):
+    # Remove words shorter than 3 characters
+    return [word for word in words if len(word) >= minimum_length]
+
+words = obtain_words(Path("diabetes.txt").read_text().lower())
+filtered_words = filter_words(words)
+pprint(filtered_words)