fixed code to get marginal cpc curve to start from origin and moved graphs to show cpc even when breakeven is not reached

marginal_cpc_calculator.py

@@ -6,8 +6,10 @@ import pandas as pd
 def hello():
     print ("world!")
 
-def polynomial_func(x, a,b,c,d):
-    y = a * x - b * x**2 + c * x**3 + d
+# def polynomial_func(x, a,b,c,d):
+#     y = a * x - b * x**2 + c * x**3 + d
+def polynomial_func(x, a,b,c):
+    y = a * x - b * x**2 + c * x**3
     return y
 
 def get_country_metrics(country,min_date='2023-07-01',max_date='2023-09-01'):
@@ -73,14 +75,18 @@ def calculate_max_spend(df,min_date,max_date,
     
     try:
         output_msg=[]
-        plt.style.use('ggplot')
+        plt.style.use('fivethirtyeight')
         fig = plt.figure(figsize=(18,6))  
                       
-        params, cv = curve_fit(polynomial_func, df_temp['cum_cost'],df_temp['marginal_income'].fillna(0), p0=(1, 1,1,1))
-        a,b,c,d = params
+        # params, cv = curve_fit(polynomial_func, df_temp['cum_cost'],df_temp['marginal_income'].fillna(0), p0=(1, 1,1,1))
+        # a,b,c,d = params
+        params, cv = curve_fit(polynomial_func, df_temp['cum_cost'],df_temp['marginal_income'].fillna(0), p0=(1, 1,1))
+        a,b,c = params
+        
 
         # determine quality of the fit
-        squaredDiffs = np.square(df_temp['marginal_income'].fillna(0) - polynomial_func(df_temp['cum_cost'], a,b,c,d))
+        # squaredDiffs = np.square(df_temp['marginal_income'].fillna(0) - polynomial_func(df_temp['cum_cost'], a,b,c,d))
+        squaredDiffs = np.square(df_temp['marginal_income'].fillna(0) - polynomial_func(df_temp['cum_cost'], a,b,c))
         squaredDiffsFromMean = np.square(df_temp['marginal_income'].fillna(0) - np.mean(df_temp['marginal_income'].fillna(0)))
         rSquared = 1 - np.sum(squaredDiffs) / np.sum(squaredDiffsFromMean)
 
@@ -90,12 +96,16 @@ def calculate_max_spend(df,min_date,max_date,
 
         # inspect the parameters
         if pprint==True:
-            output_msg.append(f"Marginal income equation Y = {a} * x - {b} * x^2 + {c} * x^3 + {d}")
+            # output_msg.append(f"Marginal income equation Y = {a} * x - {b} * x^2 + {c} * x^3 + {d}")
+            output_msg.append(f"Marginal income equation Y = {a} * x - {b} * x^2 + {c} * x^3")
 
         # calculate max costs when it becomes negative ROAS
+        # df_marginal = pd.DataFrame(zip(np.arange(500000), 
+        #                                polynomial_func(np.arange(500000), a,b,c,d)
+        #                               )).rename(columns={0:'cumulative_cost',1:'marginal_income'})
         df_marginal = pd.DataFrame(zip(np.arange(500000), 
-                                       polynomial_func(np.arange(500000), a,b,c,d)
-                                      )).rename(columns={0:'cumulative_cost',1:'marginal_income'})
+                                       polynomial_func(np.arange(500000), a,b,c)
+                                      )).rename(columns={0:'cumulative_cost',1:'marginal_income'})        
         # join actuals to get the full picture
         _ = df_temp[['cost','cpc','cum_cost', 'cum_clicks', 'cum_cpc', 'cum_revenue', 'cum_income']]
         # converting cost to integer in order to join with the marginal dataset
@@ -136,32 +146,34 @@ def calculate_max_spend(df,min_date,max_date,
             output_msg.append(f"For this spend, marginal_cpc={marginal_cpc_HAS}, cumulative_clicks={cum_clicks_HAS}, Average_cpc={cum_cpc_HAS}, cumulative_revenue={cum_revenue_HAS}")
             output_msg.append(f"Total amount spent in negative ROAS={total_negative_roas_spend}")
             # print (output_msg)
-            try:
-                ax1 = fig.add_subplot(121);
-                plt.scatter(df_temp['cum_cost'],df_temp['cpc']);
-                plt.axhline(1*cvr*aov,color='black',linestyle='--');plt.axhline(1*cvr*aov*pc,color='blue',linestyle='--');
-                plt.annotate(f'Any clicks above {np.round(cvr*aov,2)} SEK cpc has negative ROAS \n Above {np.round(cvr*aov*pc,2)} SEK is negative PC',size=12,xy=[0,40], color="black")
-                plt.xlabel('cumulative cost'); plt.ylabel('cpc')
-                # ax2.axes.get_xaxis().set_visible(False)
-                ax1.title.set_text('CPC for at different spend levels');
-            except:
-                pass            
-            try:
-                ax2 = fig.add_subplot(122)
-                plt.plot(df_temp['cum_cost'],df_temp['marginal_income'], '.', label="data")
-                plt.plot(df_temp['cum_cost'], polynomial_func(df_temp['cum_cost'], a,b,c,d), '--', color='blue', label="fitted")
-                plt.xlabel('cumulative cost'); plt.ylabel('marginal income')
-                ax2.title.set_text('Net income at different spend levels')
-            except:
-                pass
     else:
             marginal_cpc,cum_clicks,cum_cpc,cum_revenue = np.nan, np.nan, np.nan, np.nan
             total_negative_roas_spend=np.nan
             if pprint==True:
+                output_msg.append(f"Not enough data for mCPC analysis. Max threshold resulted in {max_spend_threshold}. Highest amount spent during this period is: {highest_amount_spent}") 
                 print (f"Not enough data for mCPC analysis. Max threshold resulted in {max_spend_threshold}. Highest amount spent during this period is: {highest_amount_spent}") 
-    #     return df_marginal
+    try:
+        ax1 = fig.add_subplot(121);
+        plt.scatter(df_temp['cum_cost'],df_temp['cpc'],color='black');
+        plt.axhline(1*cvr*aov,color='red',linestyle='--');plt.axhline(1*cvr*aov*pc,color='blue',linestyle='--');
+        plt.annotate(f'Any clicks above {np.round(cvr*aov,2)} SEK cpc has negative ROAS \n Above {np.round(cvr*aov*pc,2)} SEK is negative PC',size=12,xy=[0,40], color="black")
+        plt.xlabel('Cumulative ad spend that month (in SEK)'); plt.ylabel('Cost per individual click (in SEK)')
+        # ax2.axes.get_xaxis().set_visible(False)
+        ax1.title.set_text('CPC for at different spend levels');
+    except:
+        pass            
+    try:
+        ax2 = fig.add_subplot(122)
+        plt.plot(df_temp['cum_cost'],df_temp['marginal_income'], '.', label="data", color='r')
+        # plt.plot(df_temp['cum_cost'], polynomial_func(df_temp['cum_cost'], a,b,c,d), '--', color='blue', label="fitted")
+        plt.plot(df_temp['cum_cost'], polynomial_func(df_temp['cum_cost'], a,b,c), '--', color='blue', label="fitted")
+        plt.xlabel('cumulative cost'); plt.ylabel('marginal income')
+        ax2.title.set_text('Net income at different spend levels')
+    except:
+        pass    
     values = (max_spend_threshold,highest_amount_spent,total_negative_roas_spend,marginal_cpc,cum_clicks,cum_cpc,cum_revenue,rSquared)
     return fig,output_msg,values
+    # return fig,output_msg,values,df_marginal
 
 def loop_mCPC_countries(df,min_date,max_date,
                         country_list=['UK', 'DE', 'US', 'NL', 'SE', 'CH', 'BE', 'EU', 'FR', 'AU'],