Spaces:
Sleeping
Sleeping
Update pages/Data Collection.py
Browse files- pages/Data Collection.py +125 -6
pages/Data Collection.py
CHANGED
|
@@ -1846,8 +1846,6 @@ elif st.session_state.current_page == "explore_csv":
|
|
| 1846 |
""", unsafe_allow_html=True)
|
| 1847 |
|
| 1848 |
st.code("""
|
| 1849 |
-
import pandas as pd
|
| 1850 |
-
|
| 1851 |
# Sample DataFrame
|
| 1852 |
data = pd.DataFrame({
|
| 1853 |
'sepal_length': [1.5, 1.4, 1.5],
|
|
@@ -1983,14 +1981,135 @@ elif st.session_state.current_page == "explore_json":
|
|
| 1983 |
|
| 1984 |
elif st.session_state.current_page == "explore_xml":
|
| 1985 |
st.markdown("""
|
| 1986 |
-
<h3 style="color: #
|
| 1987 |
""", unsafe_allow_html=True)
|
|
|
|
| 1988 |
st.write("""
|
| 1989 |
-
XML
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1990 |
""")
|
| 1991 |
-
if st.button("Go Back"):
|
| 1992 |
-
navigate_to("main")
|
| 1993 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1994 |
|
| 1995 |
#--------------------------------------------------------- HTML --------------------------------------------------------------------------------
|
| 1996 |
|
|
|
|
| 1846 |
""", unsafe_allow_html=True)
|
| 1847 |
|
| 1848 |
st.code("""
|
|
|
|
|
|
|
| 1849 |
# Sample DataFrame
|
| 1850 |
data = pd.DataFrame({
|
| 1851 |
'sepal_length': [1.5, 1.4, 1.5],
|
|
|
|
| 1981 |
|
| 1982 |
elif st.session_state.current_page == "explore_xml":
|
| 1983 |
st.markdown("""
|
| 1984 |
+
<h3 style="color: #BB3385;">Extensible Markup Language(XML)</h3>
|
| 1985 |
""", unsafe_allow_html=True)
|
| 1986 |
+
|
| 1987 |
st.write("""
|
| 1988 |
+
- **XML (Extensible Markup Language)** is a markup language used to store and transport data.
|
| 1989 |
+
- It is designed to be self-descriptive, making it easy to read and understand.
|
| 1990 |
+
- XML uses a tree structure where data is organized into nested elements.
|
| 1991 |
+
- Commonly used for:
|
| 1992 |
+
- Configuration files
|
| 1993 |
+
- Data interchange between systems
|
| 1994 |
+
- Storing structured data
|
| 1995 |
""")
|
|
|
|
|
|
|
| 1996 |
|
| 1997 |
+
st.markdown("""
|
| 1998 |
+
<h3 style="color: #5b2c6f;">Element-wise XML Structure</h3>
|
| 1999 |
+
""", unsafe_allow_html=True)
|
| 2000 |
+
|
| 2001 |
+
st.write("""
|
| 2002 |
+
An element-wise XML structure organizes data into nested elements, where each piece of information is an individual element.""")
|
| 2003 |
+
|
| 2004 |
+
st.code("""
|
| 2005 |
+
<items>
|
| 2006 |
+
<item>
|
| 2007 |
+
<name>Item 1</name>
|
| 2008 |
+
<price>100</price>
|
| 2009 |
+
<category>Category A</category>
|
| 2010 |
+
</item>
|
| 2011 |
+
<item>
|
| 2012 |
+
<name>Item 2</name>
|
| 2013 |
+
<price>200</price>
|
| 2014 |
+
<category>Category B</category>
|
| 2015 |
+
</item>
|
| 2016 |
+
</items>
|
| 2017 |
+
""", language="xml")
|
| 2018 |
+
|
| 2019 |
+
st.code("""
|
| 2020 |
+
|
| 2021 |
+
# Reading an element-wise XML file
|
| 2022 |
+
df = pd.read_xml('element_structure.xml', xpath='/items/item')
|
| 2023 |
+
print(df)
|
| 2024 |
+
""", language="python")
|
| 2025 |
+
|
| 2026 |
+
st.write("""
|
| 2027 |
+
**Output DataFrame**:
|
| 2028 |
+
""")
|
| 2029 |
+
|
| 2030 |
+
st.table({
|
| 2031 |
+
'name': ['Item 1', 'Item 2'],
|
| 2032 |
+
'price': [100, 200],
|
| 2033 |
+
'category': ['Category A', 'Category B']
|
| 2034 |
+
})
|
| 2035 |
+
|
| 2036 |
+
st.write("""
|
| 2037 |
+
### Explanation of the `xpath` Parameter:
|
| 2038 |
+
- `xpath='/items/item'`: Extracts all `<item>` elements from within `<items>`.
|
| 2039 |
+
- Useful for XML structures with data organized by child elements.
|
| 2040 |
+
""")
|
| 2041 |
+
|
| 2042 |
+
|
| 2043 |
+
st.markdown("""
|
| 2044 |
+
<h3 style="color: #5b2c6f;">Attribute XML Structure</h3>
|
| 2045 |
+
""", unsafe_allow_html=True)
|
| 2046 |
+
|
| 2047 |
+
st.write("""
|
| 2048 |
+
An attribute XML structure stores data as attributes of tags, rather than as child elements.""")
|
| 2049 |
+
|
| 2050 |
+
st.code("""
|
| 2051 |
+
<items>
|
| 2052 |
+
<item name="Item 1" price="100" category="Category A" />
|
| 2053 |
+
<item name="Item 2" price="200" category="Category B" />
|
| 2054 |
+
</items>
|
| 2055 |
+
""", language="xml")
|
| 2056 |
+
|
| 2057 |
+
st.code("""
|
| 2058 |
+
|
| 2059 |
+
# Reading an attribute-based XML file
|
| 2060 |
+
df = pd.read_xml('attribute_structure.xml', xpath='/items/item')
|
| 2061 |
+
print(df)
|
| 2062 |
+
""", language="python")
|
| 2063 |
+
|
| 2064 |
+
st.write("""
|
| 2065 |
+
**Output DataFrame**:
|
| 2066 |
+
""")
|
| 2067 |
+
|
| 2068 |
+
st.table({
|
| 2069 |
+
'name': ['Item 1', 'Item 2'],
|
| 2070 |
+
'price': [100, 200],
|
| 2071 |
+
'category': ['Category A', 'Category B']
|
| 2072 |
+
})
|
| 2073 |
+
|
| 2074 |
+
st.write("""
|
| 2075 |
+
### Explanation of the `xpath` Parameter:
|
| 2076 |
+
- `xpath='/items/item'`: Extracts attributes of `<item>` elements.
|
| 2077 |
+
- Useful for XML structures where data is stored in attributes instead of nested elements.
|
| 2078 |
+
""")
|
| 2079 |
+
|
| 2080 |
+
st.markdown("""
|
| 2081 |
+
<h3 style="color: #5b2c6f;">Exporting Element-wise XML Structure</h3>
|
| 2082 |
+
""", unsafe_allow_html=True)
|
| 2083 |
+
|
| 2084 |
+
st.code("""
|
| 2085 |
+
|
| 2086 |
+
# Sample DataFrame
|
| 2087 |
+
data = pd.DataFrame({
|
| 2088 |
+
'name': ['Item 1', 'Item 2'],
|
| 2089 |
+
'price': [100, 200],
|
| 2090 |
+
'category': ['Category A', 'Category B']
|
| 2091 |
+
})
|
| 2092 |
+
|
| 2093 |
+
# Export the DataFrame to an element-wise XML file
|
| 2094 |
+
data.to_xml('element_structure.xml', index=False, root_name='items', row_name='item')
|
| 2095 |
+
""", language="python")
|
| 2096 |
+
|
| 2097 |
+
st.markdown("""
|
| 2098 |
+
<h3 style="color: #5b2c6f;">Exporting Attribute XML Structure</h3>
|
| 2099 |
+
""", unsafe_allow_html=True)
|
| 2100 |
+
|
| 2101 |
+
st.code("""
|
| 2102 |
+
|
| 2103 |
+
# Sample DataFrame
|
| 2104 |
+
data = pd.DataFrame({
|
| 2105 |
+
'name': ['Item 1', 'Item 2'],
|
| 2106 |
+
'price': [100, 200],
|
| 2107 |
+
'category': ['Category A', 'Category B']
|
| 2108 |
+
})
|
| 2109 |
+
|
| 2110 |
+
# Export the DataFrame to an attribute-based XML file
|
| 2111 |
+
data.to_xml('attribute_structure.xml', index=False, root_name='items', row_name='item', attr_cols=['name', 'price', 'category'])
|
| 2112 |
+
""", language="python")
|
| 2113 |
|
| 2114 |
#--------------------------------------------------------- HTML --------------------------------------------------------------------------------
|
| 2115 |
|