CsvImport.py

import pandas as pd
import matplotlib.pyplot as plt

# Load data from a CSV file
# Replace 'database.csv' with the path to your CSV file
#csv_file_path = r'C:\Users\RomeoNdlovu\OneDrive - IBM\Documents\TeleCom.csv'
csv_file_path = 'TeleCom.csv'
data = pd.read_csv(csv_file_path)

# Extract all numeric columns (ignoring non-numeric ones like strings)
numeric_data = data.select_dtypes(include=['number'])

# Create a list of all datasets
all_data = [numeric_data[col].dropna().tolist() for col in numeric_data.columns]

df = pd.DataFrame(data)
total_score = df["Salary"].sum()
print(f"The total Salary:R{total_score}")

max_tax = df["TaxDeduction"].max()
print(f"The maximum TaxDeduction:R{max_tax}")

mean_tax = df["TaxDeduction"].mean()
print(f"The mean TaxDeduction:R{mean_tax}")

groupby_gendercount = df.groupby('Gender')["Gender"].count()
print(f" Groupby Gender and show Count:{groupby_gendercount}")

groupby_gendersalary = df.groupby("Gender")["Salary"].mean()
print(f" Groupby Gender and their mean salary: R{groupby_gendersalary}")

groupby_gendersalarymax = df.groupby("Gender")["Salary"].max()
print(f" Groupby Gender and their max salary: R{groupby_gendersalarymax}")

groupby_gendersalarymin = df.groupby("Gender")["Salary"].min()
print(f" Groupby Gender and their min salary: R{groupby_gendersalarymin}")

groupby_gendertax = df.groupby("Gender")["TaxDeduction"].max()
print(f" Groupby Gender and their mean salary: R{groupby_gendertax}")

groupby_genderindepartment = df.groupby("Department")["Gender"].count()
print(f" Groupby Department and show Count:{groupby_genderindepartment}")

#mode_salary = df.mode()
#print(f"Mode of salary:{mode_salary}")

#describedata = df.describe()
#print(f"Show description:{describedata}")

'''plt.hist(df["Salary"])
plt.title("Salary Distribution")
plt.xlabel("Salary")
plt.ylabel("Frequency distribution")
plt.show()'''

#Bar charts oftern represent categorical data well
employeecount_bydepartment = df["Department"].value_counts()
plt.bar(employeecount_bydepartment.index,employeecount_bydepartment.values)
plt.title("No. of Employees in Department")
plt.xlabel("Deparment")
plt.ylabel("Employee Count")
plt.show()

corr = df["Salary"].corr(df["TaxDeduction"])
print(f"Correlation between Salary and Tax: {corr:.2f}")