Spaces:
Sleeping
Sleeping
Delete pages/page2.py
Browse files- pages/page2.py +0 -135
pages/page2.py
DELETED
@@ -1,135 +0,0 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
|
3 |
-
def background():
|
4 |
-
st.markdown(f"""
|
5 |
-
<style>
|
6 |
-
/* Set the background image for the entire app */
|
7 |
-
.stApp {{
|
8 |
-
background-color:rgba(96, 155, 124, 0.5);
|
9 |
-
background-size: 1300px;
|
10 |
-
background-repeat: no-repeat;
|
11 |
-
background-attachment: fixed;
|
12 |
-
background-position: center;
|
13 |
-
}}
|
14 |
-
|
15 |
-
</style>
|
16 |
-
""", unsafe_allow_html=True)
|
17 |
-
def page2():
|
18 |
-
background()
|
19 |
-
st.title("Data Collection")
|
20 |
-
st.header("1. What is Data?")
|
21 |
-
st.write(
|
22 |
-
"Data refers to raw facts and figures that are collected, stored, and analyzed to derive insights. "
|
23 |
-
"It serves as the foundation for any machine learning model."
|
24 |
-
)
|
25 |
-
|
26 |
-
st.header("2. Types of Data")
|
27 |
-
data_type = st.radio(
|
28 |
-
"Select a type of data to learn more:",
|
29 |
-
("Structured", "Unstructured", "Semi-Structured")
|
30 |
-
)
|
31 |
-
|
32 |
-
if data_type == "Structured":
|
33 |
-
st.subheader("Structured Data")
|
34 |
-
st.write(
|
35 |
-
"Structured data is highly organized and easily searchable within databases. "
|
36 |
-
"It includes rows and columns, such as in relational databases."
|
37 |
-
)
|
38 |
-
|
39 |
-
st.write("Data Formats:")
|
40 |
-
format_selected = st.radio(
|
41 |
-
"Select a format to explore further:",
|
42 |
-
("Excel", "CSV")
|
43 |
-
)
|
44 |
-
|
45 |
-
if format_selected == "Excel":
|
46 |
-
# Excel Data Format Section
|
47 |
-
st.subheader("Excel Data Format")
|
48 |
-
st.write("*What is it?*")
|
49 |
-
st.write(
|
50 |
-
"Excel files are spreadsheets used to organize and analyze data in rows and columns. "
|
51 |
-
"They are widely used due to their user-friendly nature and support for various data types."
|
52 |
-
)
|
53 |
-
|
54 |
-
st.write("*How to Read Excel Files?*")
|
55 |
-
st.code(
|
56 |
-
"""
|
57 |
-
import pandas as pd
|
58 |
-
# Reading an Excel file
|
59 |
-
df = pd.read_excel('file.xlsx')
|
60 |
-
print(df.head())
|
61 |
-
""",
|
62 |
-
language="python"
|
63 |
-
)
|
64 |
-
|
65 |
-
st.write("*Common Issues When Handling Excel Files*")
|
66 |
-
st.write(
|
67 |
-
"""
|
68 |
-
- Missing or corrupted files
|
69 |
-
- Version incompatibilities
|
70 |
-
- Incorrect file paths
|
71 |
-
- Handling large Excel files
|
72 |
-
"""
|
73 |
-
)
|
74 |
-
|
75 |
-
st.write("*How to Overcome These Errors/Issues?*")
|
76 |
-
st.write(
|
77 |
-
"""
|
78 |
-
- Use proper error handling with try-except.
|
79 |
-
- Convert Excel files to CSV for better compatibility.
|
80 |
-
- Use libraries like openpyxl or xlrd for specific Excel versions.
|
81 |
-
- Break large files into smaller chunks for processing.
|
82 |
-
"""
|
83 |
-
)
|
84 |
-
|
85 |
-
# Button to open Jupyter Notebook or PDF
|
86 |
-
if st.button("Open Excel Documentation"):
|
87 |
-
st.write("Download the [documentation notebook](path/to/excel_notebook.ipynb) or [PDF](path/to/excel_documentation.pdf).")
|
88 |
-
|
89 |
-
elif format_selected == "CSV":
|
90 |
-
# CSV Data Format Section
|
91 |
-
st.subheader("CSV Data Format")
|
92 |
-
st.write("*What is it?*")
|
93 |
-
st.write(
|
94 |
-
"CSV (Comma-Separated Values) files store tabular data in plain text, where each line represents a record, "
|
95 |
-
"and fields are separated by commas."
|
96 |
-
)
|
97 |
-
|
98 |
-
st.write("*How to Read CSV Files?*")
|
99 |
-
st.code(
|
100 |
-
"""
|
101 |
-
import pandas as pd
|
102 |
-
# Reading a CSV file
|
103 |
-
df = pd.read_csv('file.csv')
|
104 |
-
print(df.head())
|
105 |
-
""",
|
106 |
-
language="python"
|
107 |
-
)
|
108 |
-
|
109 |
-
st.write("*Common Issues When Handling CSV Files*")
|
110 |
-
st.write(
|
111 |
-
"""
|
112 |
-
- Encoding issues (e.g., UTF-8, ISO-8859-1)
|
113 |
-
- Inconsistent delimiters
|
114 |
-
- Missing or corrupted files
|
115 |
-
- Large file sizes causing memory errors
|
116 |
-
"""
|
117 |
-
)
|
118 |
-
|
119 |
-
st.write("*How to Overcome These Errors/Issues?*")
|
120 |
-
st.write(
|
121 |
-
"""
|
122 |
-
- Specify the correct encoding when reading files using encoding='utf-8' or similar.
|
123 |
-
- Use libraries like csv or pandas to handle different delimiters.
|
124 |
-
- Employ error handling to catch and manage missing/corrupted files.
|
125 |
-
- Use chunking to read large files in smaller parts: pd.read_csv('file.csv', chunksize=1000).
|
126 |
-
"""
|
127 |
-
)
|
128 |
-
|
129 |
-
# Button to open Jupyter Notebook or PDF
|
130 |
-
if st.button("Open CSV Documentation"):
|
131 |
-
st.write("Download the [documentation notebook](path/to/csv_notebook.ipynb) or [PDF](path/to/csv_documentation.pdf).")
|
132 |
-
|
133 |
-
if st.button("Go to Home Page"):
|
134 |
-
st.session_state.page = 'Page1'
|
135 |
-
st.experimental_rerun()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|