fix: make 801 more consistent

data/clean/f_801_wenhao.py

@@ -2,14 +2,14 @@
 import re
 
 
-def f_801(text, seed=None):
+def f_801(text, seed=0):
     """
     Scramble the letters in each word of a given text, keeping the first and last letters of each word intact.
 
     Parameters:
     text (str): The text to be scrambled.
     seed (int, optional): A seed for the random number generator to ensure reproducible results.
-                          Defaults to None (not set).
+                          Defaults to 0.
 
     Returns:
     str: The scrambled text.
@@ -28,8 +28,7 @@ def f_801(text, seed=None):
     >>> f_801("Programming is fun, isn't it?", 42)
     "Prmiangmrog is fun, isn't it?"
     """
-    if seed is not None:
-        random.seed(seed)
+    random.seed(seed)
 
     def scramble_word(match):
         word = match.group(0)

data/processed/f_1700_hanhu_wo_doc.py

@@ -33,16 +33,11 @@ def f_428(host):
     """
     if not host:
         raise ValueError("Host must be a non-empty string.")
-
     try:
-        # Fetch IP address
         ip_address = socket.gethostbyname(host)
-
-        # Fetch geolocation
         response = requests.get(f"https://ipinfo.io/{ip_address}")
         response.raise_for_status()
         geolocation = response.json()
-
         return {
             'ip_address': ip_address,
             'geolocation': geolocation

data/processed/f_1708_hanhu_wo_doc.py

@@ -44,12 +44,10 @@ def f_335(request, session_expire_time):
     - string
     """
     session_key = ''.join(random.choices(string.ascii_letters + string.digits, k=20))
-
     has_digit = any(char.isdigit() for char in session_key)
     has_letter = any(char.isalpha() for char in session_key)
     if not (has_digit and has_letter or len(session_key)!=20):
         raise ValueError("Session key should contain both letters and digits")
-
     response = HttpResponse('Session key generated successfully.')
     response.set_cookie('session_key', session_key, max_age=session_expire_time)
     return response

data/processed/f_1709_hanhu_wo_doc.py

@@ -53,10 +53,7 @@ def f_288(data):
         password = base64.b64decode(data['password']).decode()
     except (KeyError, UnicodeDecodeError, binascii.Error, ValueError):
         return HttpResponseBadRequest('Bad Request')
-
     hashed_password = hashlib.sha256(password.encode()).digest()
-
-    # Dummy authentication logic
     if username == 'admin' and hashed_password == hashlib.sha256('password'.encode()).digest():
         return HttpResponse('Login successful.')
     else:

data/processed/f_1710_hanhu_wo_doc.py

@@ -41,10 +41,8 @@ def f_400(request, header, csv_data):
     writer.writerow(header)
     writer.writerows(csv_data)
     csv_io.seek(0)
-
     response = FileResponse(csv_io, as_attachment=True, filename='data.csv')
     response['Content-Type'] = 'text/csv'
-
     return response
 
 import unittest

data/processed/f_1711_hanhu_wo_doc.py

@@ -37,15 +37,12 @@ def f_236(request, file_paths):
     'attachment; filename="files.zip"'
     """
     zip_io = io.BytesIO()
-
     with zipfile.ZipFile(zip_io, 'w') as zip_file:
         for file_path in file_paths:
             zip_file.writestr(file_path, 'This is the content of {}.'.format(file_path))
-
     zip_io.seek(0)  # Reset the file pointer to the start of the stream
     response = FileResponse(zip_io, as_attachment=True, filename='files.zip')
     response['Content-Type'] = 'application/zip'
-
     return response
 
 import unittest

data/processed/f_1712_hanhu_wo_doc.py

@@ -31,15 +31,12 @@ def f_475(template_folder):
     >>> 'POST' in app.url_map.bind('').match('/', method='POST')
     False
     """
-
     app = Flask(__name__, template_folder=template_folder)
-
     @app.route('/', methods=['POST'])
     def handle_post():
         data = request.get_json()
         logging.info(json.dumps(data))
         return render_template('index.html', data=data)
-
     return app
 
 import unittest

data/processed/f_1714_hanhu_wo_doc.py

@@ -32,15 +32,12 @@ def f_42(api_url, template_folder):
     """
     app = Flask(__name__, template_folder=template_folder)
     api = Api(app)
-
     class DataResource(Resource):
         def get(self):
             response = requests.get(api_url)
             data = response.json()
             return data
-
     api.add_resource(DataResource, '/data')
-
     return app
 
 import unittest

data/processed/f_1715_hanhu_wo_doc.py

@@ -41,46 +41,35 @@ def f_306(secret_key, template_folder):
     >>> app.config['SECRET_KEY'] == 'mysecretkey'
     True
     """
-
     app = Flask(__name__, template_folder=template_folder)
     app.config['SECRET_KEY'] = secret_key
-
     login_manager.init_app(app)
-
     class User(UserMixin):
         def __init__(self, username, password):
             self.id = username
             self.password_hash = generate_password_hash(password)
-
         def check_password(self, password):
             return check_password_hash(self.password_hash, password)
-
     @app.route('/login', methods=['GET', 'POST'])
     def login():
         form = LoginForm()
         if form.validate_on_submit():
             user = User(form.username.data, form.password.data)
             login_user(user)
             return redirect(url_for('protected'))
-
         return render_template('login.html', form=form)
-
     @app.route('/logout')
     @login_required
     def logout():
         logout_user()
         return redirect(url_for('login'))
-
     @app.route('/protected')
     @login_required
     def protected():
         return 'Logged in as: ' + current_user.id
-
-    # Mock user loader for testing
     @login_manager.user_loader
     def load_user(user_id):
         return User(user_id, 'password')
-
     return app
 
 import unittest

data/processed/f_1716_hanhu_wo_doc.py

@@ -35,18 +35,14 @@ def f_548(smtp_server, smtp_port, smtp_user, smtp_password, template_folder):
     app.config['MAIL_USERNAME'] = smtp_user
     app.config['MAIL_PASSWORD'] = smtp_password
     app.config['MAIL_USE_TLS'] = True
-
     mail = Mail()
     mail.init_app(app)
-
     @app.route('/send_mail')
     def send_mail():
         msg = Message('Hello', sender='[email protected]', recipients=['[email protected]'])
         msg.body = 'Hello Flask message sent from Flask-Mail'
         mail.send(msg)
-
         return 'Mail sent!'
-
     return app
 
 import unittest

data/processed/f_1723_hanhu_w_doc.py

@@ -40,34 +40,21 @@ def f_503(data, column, outlier_z_score):
     >>> isinstance(f_503(data, column, 3.0)[2], tuple)
     True
     """
-    # Copy the data to avoid modifying the original array
     data_copy = np.copy(data)
     column_data = data_copy[:, column]
-
-    # Standardize the data to have a mean of 0 and a standard deviation of 1
     scaler = StandardScaler()
     standardized_data = scaler.fit_transform(column_data.reshape(-1, 1))
-
-    # Calculate the Z-scores
     z_scores = np.abs(stats.zscore(standardized_data))
-
-    # Identify the outliers
     outliers = np.where(z_scores > outlier_z_score)
     data_without_outliers = np.delete(data_copy, outliers, axis=0)
-
-    # Plot the data before and after the removal of outliers
     plt.figure(figsize=(10, 5))
-
     plt.subplot(1, 2, 1)
     plt.scatter(data_copy[:, 0], data_copy[:, 1])
     plt.title('Data with Outliers')
-
     plt.subplot(1, 2, 2)
     plt.scatter(data_without_outliers[:, 0], data_without_outliers[:, 1])
     plt.title('Data without Outliers')
-
     plt.show()
-
     return data_copy, data_without_outliers, outliers
 
 import unittest

data/processed/f_1728_hanhu_w_doc.py

@@ -45,14 +45,12 @@ def f_334(mean, std_dev, num_samples):
     samples = np.random.normal(mean, std_dev, num_samples)
     fig, ax = plt.subplots()
     ax.hist(samples, bins=30, density=True, alpha=0.6, color='g')
-
     xmin, xmax = ax.get_xlim()
     x = np.linspace(xmin, xmax, 100)
     p = norm.pdf(x, mean, std_dev)
     ax.plot(x, p, 'k', linewidth=2)
     title = "Fit results: mean = %.2f,  std = %.2f" % (mean, std_dev)
     ax.set_title(title)
-
     return samples, fig
 
 import unittest

data/processed/f_1729_hanhu_wo_doc.py

@@ -34,15 +34,12 @@ def f_57(csv_file, csv_delimiter):
     True
     """
     words = []
-
     with open(csv_file, 'r') as f:
         reader = csv.reader(f, delimiter=csv_delimiter)
         for row in reader:
             words.extend(row)
-
     word_counter = Counter(words)
     most_common_words = sorted(word_counter.items(), key=operator.itemgetter(1), reverse=True)
-
     return most_common_words
 
 import unittest

data/processed/f_1730_hanhu_w_doc.py

@@ -28,13 +28,11 @@ def f_230(numbers):
     True
     """
     sum_log_products = 0
-
     for r in range(1, len(numbers) + 1):
         combinations = itertools.combinations(numbers, r)
         for combination in combinations:
             product = reduce(lambda x, y: x * y, combination)
             sum_log_products += math.log(product)
-
     return sum_log_products
 
 import unittest

data/processed/f_1731_hanhu_w_doc.py

@@ -32,7 +32,6 @@ def f_415(num_strings, string_length):
     characters = ''.join(strings)
     character_counter = Counter(characters)
     most_common_characters = character_counter.most_common()
-
     return most_common_characters
 
 import unittest

data/processed/f_1749_hanhu_wo_doc.py

@@ -37,21 +37,16 @@ def f_478(my_dict, keys):
     """
     if len(set(keys)) != 10:
         raise ValueError("keys parameter must contain exactly 10 unique elements")
-
     for key in keys:
         my_dict[key] = random.randint(1, 100)
-
     json_filename = "updated_dictionary.json"
     txt_filename = "key_frequencies.txt"
-
     with open(json_filename, 'w') as json_file:
         json.dump(my_dict, json_file, indent=4)
-
     key_counts = Counter(my_dict.keys())
     with open(txt_filename, 'w') as txt_file:
         for key, count in key_counts.items():
             txt_file.write(f"{key}: {count}\n")
-
     return my_dict, json_filename, txt_filename
 
 import unittest

data/processed/f_1750_hanhu_w_doc.py

@@ -33,13 +33,10 @@ def f_482(my_dict):
     """
     if not isinstance(my_dict["array"], np.ndarray):
         raise TypeError
-
     SCALER = MinMaxScaler()
     array = my_dict['array'].reshape(-1, 1)
     normalized_array = SCALER.fit_transform(array).reshape(-1)
-
     my_dict['normalized_array'] = normalized_array
-
     return my_dict
 
 import unittest

data/processed/f_1753_hanhu_w_doc.py

@@ -40,15 +40,12 @@ def f_239(mu, sigma, sample_size):
     True
     """
     samples = np.random.normal(mu, sigma, sample_size)
-
-    # Plotting the histogram of the samples
     plt.hist(samples, bins=30, alpha=0.75, color='blue')
     plt.title('Histogram of Generated Samples')
     plt.xlabel('Sample values')
     plt.ylabel('Frequency')
     plt.grid(True)
     plt.show()
-
     return samples
 
 import unittest

data/processed/f_1754_hanhu_wo_doc.py

@@ -29,17 +29,14 @@ def f_441(directory, backup_directory):
     True
     """
     copied_files = []
-
     if not os.path.exists(backup_directory):
         os.makedirs(backup_directory)
-
     for filename in os.listdir(directory):
         if filename.endswith('.json'):
             src = os.path.join(directory, filename)
             dst = os.path.join(backup_directory, filename)
             shutil.copy(src, dst)
             copied_files.append(dst)
-
     return copied_files
 
 import unittest

data/processed/f_1756_hanhu_w_doc.py

@@ -27,7 +27,6 @@ def f_405():
     """
     X = np.linspace(-10, 10, 400)
     Y = X**2
-
     plt.figure()
     plt.plot(X, Y)
     plt.title('y = x^2')

data/processed/f_1759_hanhu_w_doc.py

@@ -28,10 +28,8 @@ def f_5(my_list):
     """
     random_number = random.randint(0, 100)
     my_list.append(random_number)
-
     size = sum(my_list)
     random_array = np.random.rand(size)
-
     return random_array
 
 import unittest

data/processed/f_1763_hanhu_wo_doc.py

@@ -31,15 +31,12 @@ def f_199(LETTERS, n):
     """
     combinations = list(itertools.combinations(LETTERS, n))
     letter_counts = defaultdict(int)
-
     for combination in combinations:
         for letter in combination:
             letter_counts[letter] += 1
-
     filename = f'letter_combinations_{random.randint(1, 100)}.json'
     with open(filename, 'w') as f:
         json.dump(letter_counts, f)
-
     return filename
 
 import unittest

data/processed/f_1764_hanhu_wo_doc.py

@@ -34,7 +34,6 @@ def f_668(ROOT_DIR, DEST_DIR, SPECIFIC_HASH):
     True
     """
     files_moved = 0
-
     os.makedirs(DEST_DIR, exist_ok=True)
     for filename in glob.glob(os.path.join(ROOT_DIR, '*')):
         if not os.path.exists(filename) or os.path.isdir(filename):