clean up awesome data explorer

gallery/awesome_data_explorer/app.py → gallery/awesome_data_explorer/awesome_data_explorer.py

@@ -6,7 +6,9 @@
 Author: [Ali Avni Cirik](https://www.linkedin.com/in/aliavnicirik)\n
 Source: [Github](https://github.com/aliavni/awesome-data-explorer)
 """
+import logging
 from pathlib import Path
+from typing import Dict, Tuple, Union
 
 import altair as alt
 import git
@@ -18,6 +20,7 @@
 
 @st.cache
 def get_awesome_data_repo():
+    """Clones the data catalogue"""
     try:
         git.Git(".").clone("https://github.com/awesomedata/apd-core")
     except git.GitCommandError:
@@ -26,38 +29,68 @@ def get_awesome_data_repo():
 
 
 @st.cache
-def get_categories_and_file_names() -> dict:
-    p = Path("apd-core/core")
-    category_files = {}
-    for i in p.glob("**/*"):
+def get_categories_and_file_names() -> Dict:
+    """Returns a dictionary of categories and files
+
+    Returns
+    -------
+    Dict
+        Key is the name of the category, value is a dictionary with information on files in that \
+        category
+    """
+    path = Path("apd-core/core")
+    category_files: Dict = {}
+    for i in path.glob("**/*"):
         if i.is_dir():
             continue
 
         category, file_name = i.parts[-2:]
 
         file = Path("apd-core/core") / category / file_name
+        try:
+            with file.open() as open_file:
+                data_info = yaml.load(open_file.read(), Loader=yaml.FullLoader)
 
-        with file.open() as f:
-            data_info = yaml.load(f.read(), Loader=yaml.FullLoader)
-
-        if category in category_files:
-            category_files[category][file_name] = data_info
-        else:
-            category_files[category] = {file_name: data_info}
+            if category in category_files:
+                category_files[category][file_name] = data_info
+            else:
+                category_files[category] = {file_name: data_info}
+        except UnicodeDecodeError as err:
+            logging.exception("Error. Could not read %s", file.name, exc_info=err)
 
     return category_files
 
 
-def get_data_info(category: str, file_name: str) -> dict:
-    p = Path("apd-core/core") / category / file_name
+def get_data_info(category: str, file_name: str) -> Dict:
+    """Returns a dictionary of information on the specified file
 
-    with p.open() as f:
-        data = yaml.load(f.read(), Loader=yaml.FullLoader)
+    Parameters
+    ----------
+    category : str
+        The name of the category, like 'Sports'
+    file_name : str
+        A name of a file
 
+    Returns
+    -------
+    Dict
+        Information on the file
+    """
+    path = Path("apd-core/core") / category / file_name
+
+    with path.open() as open_file:
+        data = yaml.load(open_file.read(), Loader=yaml.FullLoader)
     return data
 
 
-def create_info_table(selected_data_info):
+def create_info_table(selected_data_info: Dict):
+    """Writes the information to the table
+
+    Parameters
+    ----------
+    selected_data_info : Dict
+        The information to show
+    """
     info_table = pd.DataFrame()
 
     data_description = selected_data_info["description"]
@@ -79,21 +112,34 @@ def create_info_table(selected_data_info):
 
 
 @st.cache()
-def check_url(url: str):
+def check_url(url: str) -> Tuple[bool, Union[str, requests.Response]]:
+    """Returns information on the availability of the url
+
+    Parameters
+    ----------
+    url : str
+        The url to test
+
+    Returns
+    -------
+    Tuple[bool, Union[str, Response]]
+        Whether the url is available and a string reponse
+    """
     try:
         response = requests.head(url, allow_redirects=False)
         return True, response
-    except requests.exceptions.SSLError as e:
+    except requests.exceptions.SSLError:
         return False, "SSL error"
-    except requests.exceptions.ConnectionError as e:
+    except requests.exceptions.ConnectionError:
         return False, "Connection error"
-    except requests.exceptions.InvalidSchema as e:
+    except requests.exceptions.InvalidSchema:
         return False, "Invalid schema"
-    except requests.exceptions.MissingSchema as e:
+    except requests.exceptions.MissingSchema:
         return check_url("https://" + url)
 
 
 def show_homepage(data_info):
+    """Shows information on the availability of the url to the user"""
     homepage = data_info["homepage"]
 
     if homepage.startswith("http:"):
@@ -118,6 +164,7 @@ def show_homepage(data_info):
 
 
 def main():
+    """Run this to run the programme"""
     st.title("Awesome Data Explorer")
     st.markdown("This app explores data in the Awesome Public Datasets repository.")
 

gallery/global_power_plant_database/global_power_plant_database.py

@@ -1,4 +1,4 @@
-"""This app demonstrates the use of the awesome [deck.gl](https://deck.gl/#/) framework for visual
+"""This app demonstrates the use of the awesome [deck.gl]() framework for visual
 exploratory data analysis of large datasets.
 
 Deck.gl is now (as of Streamlit v. 0.53) supported via the

mypy.ini

@@ -40,3 +40,5 @@ ignore_missing_imports=True
 ignore_missing_imports=True
 [mypy-pydeck.*]
 ignore_missing_imports=True
+[mypy-git.*]
+ignore_missing_imports=True

package/awesome_streamlit/database/apps_in_gallery.py

@@ -22,7 +22,7 @@
 APPS_IN_GALLERY = [
     Resource(
         name="Awesome Data Explorer",
-        url=GITHUB_RAW_GALLERY_URL + "awesome_data_explorer/app.py",
+        url=GITHUB_RAW_GALLERY_URL + "awesome_data_explorer/awesome_data_explorer.py",
         tags=[tags.CODE, tags.APP_IN_GALLERY],
         is_awesome=True,
         author=authors.ALI_AVNI_CIRIK,

scripts/issues/issue_duplicate_widget.py

@@ -0,0 +1,15 @@
+import streamlit as st
+import time
+
+slider_ph = st.empty()
+info_ph = st.empty()
+
+value = slider_ph.slider("slider", 0, 100, 25, 1)
+info_ph.info(value)
+
+if st.button('animate'):
+    for x in range(20):
+        time.sleep(.5)
+
+        value = slider_ph.slider("slider", 0, 100, value + 1, 1)
+        info_ph.info(value)