ralate2 commited on
Commit
14d25ab
·
verified ·
1 Parent(s): 5bc8cef

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +32 -11
app.py CHANGED
@@ -14,6 +14,18 @@ st.write(df.head()) # Inspect the first few rows to see the column names and an
14
  st.write("Missing values per column:")
15
  st.write(df.isnull().sum()) # This will show the number of missing values per column
16
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  # Debug: Check the data types of the columns to see if any columns need to be converted
18
  st.write("Data types of columns:")
19
  st.write(df.dtypes)
@@ -47,21 +59,30 @@ df['Last Modified Date Year'] = pd.to_numeric(df['Last Modified Date Year'], err
47
  # Convert object columns to category or proper types
48
  for col in df.select_dtypes(include='object').columns:
49
  df[col] = df[col].astype('category') # Convert strings to categories to improve performance
 
50
 
51
  # Check for missing values after conversion
52
  st.write("Missing values after conversion:")
53
  st.write(df.isnull().sum()) # This will show the number of missing values per column
54
 
 
 
 
 
 
 
 
 
55
  # Debug: Check the cleaned data after conversion
56
  st.write("Cleaned data preview:")
57
  st.write(df.head())
58
 
59
- # Visualization 1: Bar chart of licenses by type
60
- st.subheader("Licenses by Type")
61
 
62
- # Group data by License Type
63
- category_counts = df['License Type'].value_counts().reset_index()
64
- category_counts.columns = ['License Type', 'Count']
65
 
66
  # Debug: Check the grouped data for the first chart
67
  st.write("Grouped data for licenses by type:")
@@ -70,22 +91,22 @@ st.write(category_counts.head()) # Check if data is available for plotting
70
  # Ensure category_counts is not empty before plotting
71
  if not category_counts.empty:
72
  chart1 = alt.Chart(category_counts).mark_bar().encode(
73
- x=alt.X('License Type', sort='-y', title='License Type'),
74
  y=alt.Y('Count', title='Number of Licenses'),
75
- color=alt.Color('License Type', legend=None)
76
  ).properties(
77
  width=600,
78
  height=400,
79
- title="Number of Licenses by Type"
80
  )
81
  st.altair_chart(chart1)
82
  else:
83
- st.write("No data available for the 'License Type' plot.")
84
 
85
  # Write-up for Visualization 1
86
  st.write("""
87
- **Licenses by Type**: This visualization highlights the distribution of licenses across different types.
88
- The bar chart was chosen for its simplicity in comparing counts across license types. I chose to sort types in descending order for clarity.
89
  Colors were selected to make each bar distinct, and axis labels were added for easy interpretation.
90
  If I had more time, I might add interactivity to allow users to filter by other variables.
91
  """)
 
14
  st.write("Missing values per column:")
15
  st.write(df.isnull().sum()) # This will show the number of missing values per column
16
 
17
+ # Checking for percentage of missing values
18
+ missing_percentage = (df.isnull().sum() / len(df)) * 100
19
+ st.write("Percentage of Missing Values per Column", missing_percentage)
20
+
21
+ # Dropping columns with more than 90% missing values
22
+ df.drop(columns=['Title', 'Prefix', 'Suffix', 'BusinessDBA'], inplace=True)
23
+
24
+ # Dropping rows with missing values for important columns (where missing data is below 10%)
25
+ df.dropna(subset=['_id','License Number', 'First Name', 'Middle' , 'Last Name', 'Effective Date',
26
+ 'Expiration Date', 'City', 'Zip', 'County', 'Specialty/Qualifier',
27
+ 'Controlled Substance Schedule', 'Action'], inplace=True)
28
+
29
  # Debug: Check the data types of the columns to see if any columns need to be converted
30
  st.write("Data types of columns:")
31
  st.write(df.dtypes)
 
59
  # Convert object columns to category or proper types
60
  for col in df.select_dtypes(include='object').columns:
61
  df[col] = df[col].astype('category') # Convert strings to categories to improve performance
62
+ st.write(df.dtypes)
63
 
64
  # Check for missing values after conversion
65
  st.write("Missing values after conversion:")
66
  st.write(df.isnull().sum()) # This will show the number of missing values per column
67
 
68
+
69
+ # Drop rows with any missing values
70
+ df.dropna(inplace=True)
71
+
72
+ # Verify if any missing values remain
73
+ st.write("Missing values after dropping rows with any missing values:")
74
+ st.write(df.isnull().sum()) # Verify if any missing values remain
75
+
76
  # Debug: Check the cleaned data after conversion
77
  st.write("Cleaned data preview:")
78
  st.write(df.head())
79
 
80
+ # Visualization 1: Bar chart of licenses by Status
81
+ st.subheader("Licenses by Status")
82
 
83
+ # Group data by License Status
84
+ category_counts = df['License Status'].value_counts().reset_index()
85
+ category_counts.columns = ['License Status', 'Count']
86
 
87
  # Debug: Check the grouped data for the first chart
88
  st.write("Grouped data for licenses by type:")
 
91
  # Ensure category_counts is not empty before plotting
92
  if not category_counts.empty:
93
  chart1 = alt.Chart(category_counts).mark_bar().encode(
94
+ x=alt.X('License Status', sort='-y', title='License Type'),
95
  y=alt.Y('Count', title='Number of Licenses'),
96
+ color=alt.Color('License Status', legend=None)
97
  ).properties(
98
  width=600,
99
  height=400,
100
+ title="Number of Licenses by Status"
101
  )
102
  st.altair_chart(chart1)
103
  else:
104
+ st.write("No data available for the 'License Status' plot.")
105
 
106
  # Write-up for Visualization 1
107
  st.write("""
108
+ **Licenses by Status**: This visualization highlights the distribution of licenses across status of the license.
109
+ The bar chart was chosen for its simplicity in comparing counts across license status. I chose to sort types in descending order for clarity.
110
  Colors were selected to make each bar distinct, and axis labels were added for easy interpretation.
111
  If I had more time, I might add interactivity to allow users to filter by other variables.
112
  """)