marketing_campaign.py

marketing_campaign.py

"""
Facem un program care analizeaza Campaniile de Marketing

- unealta complexa pentru analiza performantei campaniilor de marketing.

Scop:

- evalueze performanta diferitelor campanii de Marketing

- vizualizeze datele intr-un mod intuitiv si informativ

- prezicere ROI (return on investment) bazat pe performanta istorica

- simulare diferite scenarii de buget pentru a gasi nivelul optimal de investment

- ofere recomandari actionabile pentru decizii strategice de marketing.


Aplicatia noastra - calculeaza

- profit
- returnarea investitiei ROI
- costul de achizitie al clientilor
- venit per client
- profit per client
"""

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import r2_score, mean_squared_error
import io

# functie care incarca dataset dintr-un fisier source or String
def load_data(source, is_file=False):
    if is_file:
        df = pd.read_csv( source )
    else:
        df = pd.read_csv(io.StringIO(source))
    return df

def calculate_metrics( df ):

    df['Profit'] = df['Revenue_Generated'] - df['Total_Spend']
    df['ROI'] = (df['Profit'] / df['Total_Spend']) * 100;
    df['Customer_Acquisition_Cost'] = df['Total_Spend'] / df['Customers_Acquired']
    df['Revenue_per_Customer'] = df['Revenue_Generated'] / df['Customers_Acquired']
    df['Profit_per_Customer'] = df['Profit'] / df['Customers_Acquired']
    return df

def analyze_performance( df ):

    metrics = ['Profit', 'ROI', 'Customer_Acquisition_Cost', 'Revenue_per_Customer']

    results = pd.DataFrame({
          'Metric': [],
          'Best Campaign': [],
          'Best Value': [],
          'Worst Campaign': [],
          'Worst Value': []
    })

    for metric in metrics:

        if metric == 'Customer_Acquisition_Cost':
            best_idx = df[metric].idxmin()
            worst_idx = df[metric].idxmax()
        else:
            best_idx = df[metric].idxmax()
            worst_idx = df[metric].idxmin()

        results = pd.concat([results, pd.DataFrame({
            'Metric': [metric],
            'Best Campaign': [df.loc[best_idx, 'Campaign']],
            'Best Value': [df.loc[best_idx, metric]],
            'Worst Campaign': [df.loc[worst_idx, 'Campaign']],
            'Worst Value': [df.loc[worst_idx, metric]],

        })], ignore_index = True)

        print("Performance Analysis:")
        print(results)
        print("\nSummary Statistics:")
        print(df.describe())
        return results

def main():

    data = """Campaign,Total_Spend,Revenue_Generated,Customers_Acquired
Email,5000,15000,150
Social Media,7500,22500,300
Google Ads,10000,35000,500
Referral,3000,9000,100
Content MArketing,6000,18000,250"""
    df = load_data(data, is_file=False)

    df = calculate_metrics(df)

    print("Marketing Campaign Data:")
    print(df)

    performance_results = analyze_performance(df)

main()