Improve Describe-method.py with modular OOP structure and enhanced analytics

Describe-method.py

@@ -1,33 +1,57 @@
-#step 1 sample data frame
-
 import pandas as pd
+import matplotlib.pyplot as plt
+
+
+class EmployeeDataAnalyzer:
+    def __init__(self, data):
+        self.df = pd.DataFrame(data)
+
+    def display_data(self):
+        print("Displaying the DataFrame:")
+        print(self.df)
+
+    def describe_data(self):
+        print("\nDescribing the DataFrame:")
+        print(self.df.describe())
+
+    def dataset_info(self):
+        print(f"\nShape of the DataFrame: {self.df.shape}")
+        print(f"Columns in the DataFrame: {self.df.columns.tolist()}")
+        print(f"\nData Types:\n{self.df.dtypes}")
 
-data={
-    "Name":['Prince','Riya','Karan','Anjali','Rahul','Sita','Ravi','Amit'],
-    "Age":[18,20,24,31,45,53,60,70],
-    "Salary":[30000,20000,43000,40000,54000,60000,48000,58000],
-    "Performance":[5,6,7,8,9,10,4,3]
+    def categorize_performance(self):
+        def category(score):
+            if score >= 8:
+                return "High"
+            elif score >= 5:
+                return "Medium"
+            else:
+                return "Low"
+
+        self.df["Performance Category"] = self.df["Performance"].apply(category)
+        print("\nPerformance categories added.")
+        print(self.df[["Name", "Performance", "Performance Category"]])
+
+    def visualize_salary_distribution(self):
+        plt.hist(self.df["Salary"], bins=5)
+        plt.title("Salary Distribution")
+        plt.xlabel("Salary")
+        plt.ylabel("Frequency")
+        plt.show()
+
+
+# Sample Data
+data = {
+    "Name": ['Prince','Riya','Karan','Anjali','Rahul','Sita','Ravi','Amit'],
+    "Age": [18,20,24,31,45,53,60,70],
+    "Salary": [30000,20000,43000,40000,54000,60000,48000,58000],
+    "Performance": [5,6,7,8,9,10,4,3]
 }
-df = pd.DataFrame(data)
-# Display the DataFrame
-print("Displaying the DataFrame:")
-print(df)
-
-#step 2 describe method
-print("\nDescribing the DataFrame:")
-print(df.describe())
-
-'''
-1- How to use the describe method in pandas?
-The `describe()` method in pandas is used to generate descriptive statistics of a DataFrame. It
-provides a summary of the central tendency, dispersion, and shape of the dataset's distribution, excluding `NaN` values. The output includes count, mean, standard deviation, minimum, maximum, and percentiles (25%, 50%, 75%) for each numeric column.
-
-'''
-
-'''
-1-How big is your dataSet 
-2- What are the names of the columns in your dataSet?
-3- What is the data type of each column in your dataSet?
-'''
-print(f"Shape of the DataFrame: {df.shape}")
-print(f"Columns in the DataFrame: {df.columns.tolist()}")
+
+if __name__ == "__main__":
+    analyzer = EmployeeDataAnalyzer(data)
+    analyzer.display_data()
+    analyzer.describe_data()
+    analyzer.dataset_info()
+    analyzer.categorize_performance()
+    analyzer.visualize_salary_distribution()