└── PythonEDA


/PythonEDA:
--------------------------------------------------------------------------------
  1 | import pandas as pd
  2 | import matplotlib.pyplot as plt
  3 | import seaborn as sns
  4 | 
  5 | df = pd.read_csv(r"C:\Users\kumar\Downloads\Employee Sample Dataint 217 (1).csv", encoding='ISO-8859-1')
  6 | 
  7 | print(df.dtypes)
  8 | 
  9 | df['Hire Year'] = pd.to_datetime(df['Hire Date'], errors='coerce').dt.year
 10 | hire_trend = df['Hire Year'].value_counts().sort_index()
 11 | hire_trend.plot(kind='line', marker='o', title='Hiring Trend Over Years')
 12 | plt.xlabel("Year")
 13 | plt.ylabel("Number of Hires")
 14 | plt.grid(True)
 15 | plt.show()
 16 | 
 17 | gender_dept = df.groupby(['Department', 'Gender']).size().unstack()
 18 | gender_dept.plot(kind='bar', stacked=True, figsize=(10, 6), colormap='Paired')
 19 | plt.title('Gender Distribution by Department')
 20 | plt.xlabel('Department')
 21 | plt.ylabel('Number of Employees')
 22 | plt.xticks(rotation=45)
 23 | plt.legend(title='Gender')
 24 | plt.tight_layout()
 25 | plt.show()
 26 | 
 27 | print(df.columns)
 28 | 
 29 | numeric_cols = df.select_dtypes(include='number')
 30 | print(numeric_cols.columns)
 31 | 
 32 | plt.figure(figsize=(10, 6))
 33 | correlation = numeric_cols.corr()
 34 | sns.heatmap(correlation, annot=True, cmap='coolwarm', fmt=".2f")
 35 | plt.title("Correlation Between Numeric Features")
 36 | plt.tight_layout()
 37 | plt.show()
 38 | 
 39 | plt.figure(figsize=(10, 5))
 40 | sns.histplot(df['Age'], kde=True, color='skyblue', bins=20)
 41 | plt.title("Employee Age Distribution")
 42 | plt.xlabel("Age")
 43 | plt.ylabel("Frequency")
 44 | plt.tight_layout()
 45 | plt.show()
 46 | 
 47 | df['Hire Date'] = pd.to_datetime(df['Hire Date'], errors='coerce')
 48 | df['Exit Date'] = pd.to_datetime(df['Exit Date'], errors='coerce')
 49 | df['End Date'] = df['Exit Date'].fillna(pd.Timestamp.today())
 50 | df['Tenure (Years)'] = (df['End Date'] - df['Hire Date']).dt.days / 365
 51 | 
 52 | plt.figure(figsize=(10, 6))
 53 | sns.scatterplot(data=df, x='Tenure (Years)', y='Annual Salary', hue='Department', palette='tab10')
 54 | plt.title("Annual Salary vs Tenure (Years)")
 55 | plt.xlabel("Tenure in Years")
 56 | plt.ylabel("Annual Salary")
 57 | plt.tight_layout()
 58 | plt.show()
 59 | 
 60 | plt.figure(figsize=(10, 6))
 61 | sns.countplot(data=df, x='Department', hue='Gender', palette='Set1')
 62 | plt.title("Gender Distribution per Department")
 63 | plt.xticks(rotation=45)
 64 | plt.tight_layout()
 65 | plt.show()
 66 | 
 67 | emp_type_counts = df['Job Title'].value_counts()
 68 | 
 69 | plt.figure(figsize=(10, 8))
 70 | sns.barplot(
 71 |     x=emp_type_counts.values,
 72 |     y=emp_type_counts.index,
 73 |     hue=emp_type_counts.index,
 74 |     palette='Set2',
 75 |     dodge=False,
 76 |     legend=False
 77 | )
 78 | plt.xlabel("Count")
 79 | plt.ylabel("Job Title")
 80 | plt.title("Employment Type Distribution")
 81 | plt.tight_layout()
 82 | plt.show()
 83 | 
 84 | plt.figure(figsize=(8, 6))
 85 | sns.boxplot(
 86 |     data=df,
 87 |     x='Gender',
 88 |     y='Annual Salary',
 89 |     hue='Gender',
 90 |     palette='coolwarm',
 91 |     dodge=False,
 92 |     legend=False
 93 | )
 94 | plt.title("Annual Salary Distribution by Gender")
 95 | plt.tight_layout()
 96 | plt.show()
 97 | 
 98 | pivot = df.pivot_table(values='Annual Salary', index='Department', columns='Gender', aggfunc='mean')
 99 | plt.figure(figsize=(10, 6))
100 | sns.heatmap(pivot, annot=True, fmt=".0f", cmap='YlGnBu')
101 | plt.title("Average Salary by Department and Gender")
102 | plt.tight_layout()
103 | plt.show()
104 | 
105 | pivot = df.pivot_table(values='Annual Salary', index='Department', columns='Gender', aggfunc='mean')
106 | plt.figure(figsize=(10, 6))
107 | sns.heatmap(pivot, annot=True, fmt=".0f", cmap='YlGnBu')
108 | plt.title("Average Salary by Department and Gender")
109 | plt.tight_layout()
110 | plt.show()
111 | 
112 | avg_tenure = df.groupby('Department')['years'].mean().sort_values()
113 | plt.figure(figsize=(10, 5))
114 | sns.lineplot(x=avg_tenure.index, y=avg_tenure.values, marker='o')
115 | plt.xticks(rotation=45)
116 | plt.ylabel("Average Tenure (Years)")
117 | plt.title("Average Tenure by Department")
118 | plt.tight_layout()
119 | plt.show()
120 | 


--------------------------------------------------------------------------------