Add comments in flickr/photos_detail.py and some minor styling changes

Signed-off-by: Priyanshi Gaur <noxdot1134@gmail.com>
creativecommons · Mar 12, 2024 · 6f73b00 · 6f73b00
1 parent 2be88a6
commit 6f73b00
Show file tree

Hide file tree

Showing 4 changed files with 120 additions and 84 deletions.
diff --git a/analyze/data_analysis.py b/analyze/data_analysis.py
@@ -138,10 +138,10 @@ def time_trend_helper(df):
     Extract year-wise count of entries from a DataFrame.
 
     Args:
-        df (DataFrame): Input DataFrame containing dates.
+    - df (DataFrame): Input DataFrame containing dates.
 
     Returns:
-        DataFrame: DataFrame with counts of entries per year.
+    - DataFrame: DataFrame with counts of entries per year.
     """
     year_list = []
     for date_row in df["dates"][0:]:
@@ -167,7 +167,7 @@ def time_trend(csv_path):
     Generate a line graph to show the time trend of the license usage.
 
     Args:
-        csv_path (str): Path to the CSV file.
+    - csv_path (str): Path to the CSV file.
     """
     df = pd.read_csv(csv_path)
     count_df = time_trend_helper(df)
@@ -205,10 +205,10 @@ def time_trend_compile_helper(yearly_count):
     Filter yearly trend data for the years between 2018 and 2022.
 
     Args:
-        yearly_count (DataFrame): DataFrame with "year" and "Counts" columns.
+    - yearly_count (DataFrame): DataFrame with "year" and "Counts" columns.
 
     Returns:
-        DataFrame: Filtered yearly count data.
+    - DataFrame: Filtered yearly count data.
     """
     Years = np.arange(2018, 2023)
     yearly_count["year"] = list(yearly_count.index)
@@ -370,10 +370,10 @@ def view_compare_helper(df):
     Calculate maximum views of pictures under a license.
 
     Args:
-        df (DataFrame): Input DataFrame.
+    - df (DataFrame): Input DataFrame.
 
     Returns:
-        int: Maximum views.
+    - int: Maximum views.
     """
     highest_view = int(max(df["views"]))
     df = df.sort_values("views", ascending=False)

diff --git a/deviantart/deviantart_scratcher.py b/deviantart/deviantart_scratcher.py
@@ -41,8 +41,8 @@ def get_license_list():
     Provides the list of license from 2018's record of Creative Commons.
 
     Returns:
-        np.array: An array containing all license types that should be
-        searched via Programmable Search Engine.
+    - np.array: An array containing all license types that should be
+    searched via Programmable Search Engine.
     """
     # Read license data from file
     cc_license_data = pd.read_csv(f"{CWD}/legal-tool-paths.txt", header=None)
@@ -61,11 +61,11 @@ def get_request_url(license):
     """
     Provides the API Endpoint URL for specified parameter combinations.
     Args:
-        license (str): A string representing the type of license. It's a
-        segment of the URL towards the license description.
+    - license (str): A string representing the type of license. It's a
+    segment of the URL towards the license description.
 
     Returns:
-        str: The API Endpoint URL for the query specified by parameters.
+    - str: The API Endpoint URL for the query specified by parameters.
     """
     try:
         api_key = API_KEYS[API_KEYS_IND]
@@ -86,14 +86,13 @@ def get_response_elems(license):
     """
     Provides the metadata for query of specified parameters
     Args:
-        license (str):
-        A string representing the type of license. It's a segment of the URL
-        towards the license description. If not provided, it defaults to None,
-        indicating no assumption about the license type.
+    - license (str): A string representing the type of license.
+    It's a segment of the URL towards the license description. If not provided,
+    it defaults to None, indicating no assumption about the license type.
 
     Returns:
-        dict: A dictionary mapping metadata to its value provided from the API
-        query.
+    - dict: A dictionary mapping metadata to its value provided from the API
+    query.
     """
     try:
         # Make a request to the API and handle potential retries
@@ -136,10 +135,9 @@ def set_up_data_file():
 def record_license_data(license_type):
     """Writes the row for LICENSE_TYPE to the file to contain DeviantArt data.
     Args:
-        license_type(str):
-            A string representing the type of license. It's a segment of the
-            URL towards the license description. If not provided, it defaults
-            to None, indicating no assumption about the license type.
+    - license_type(str): A string representing the type of license.
+    It's a segment of the URL towards the license description. If not provided,
+    it defaults to None, indicating no assumption about the license type.
     """
     data_log = (
         f"{license_type},"

diff --git a/flickr/data_cleaning.py b/flickr/data_cleaning.py
@@ -24,8 +24,8 @@ def drop_empty_column(csv_path, new_csv_path):
     """
     Drops columns with 'Unnamed' in the name from the CSV file.
     Args:
-        csv_path (str): Path to the original CSV file.
-        new_csv_path (str): Path to save the cleaned CSV file.
+    - csv_path (str): Path to the original CSV file.
+    - new_csv_path (str): Path to save the cleaned CSV file.
     """
     df = pd.read_csv(csv_path)
     for col in df.columns:
@@ -41,8 +41,8 @@ def drop_duplicate_id(csv_path, new_csv_path):
     Drops duplicate rows based on the 'id' column from the CSV file.
 
     Args:
-        csv_path (str): Path to the original CSV file.
-        new_csv_path (str): Path to save the cleaned CSV file.
+    - csv_path (str): Path to the original CSV file.
+    - new_csv_path (str): Path to save the cleaned CSV file.
     """
     df = pd.read_csv(csv_path)
     data = df.drop_duplicates(subset=["id"])
@@ -55,10 +55,10 @@ def save_new_data(csv_path, column_name_list, new_csv_path):
     Saves specified columns from the original CSV file to a new CSV file.
 
     Args:
-        csv_path (str): Path to the original CSV file.
-        column_name_list (list of str): List of column names to be saved
-        (belongs to the existing column names from original csv)
-        new_csv_path (str): Path to save the new CSV file.
+    - csv_path (str): Path to the original CSV file.
+    - column_name_list (list of str): List of column names to be saved
+    (belongs to the existing column names from original csv)
+    - new_csv_path (str): Path to save the new CSV file.
     """
     df = pd.read_csv(csv_path)
     new_df = pd.DataFrame()