1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
##
## name: Auto Tag Campaigns with Brand
## description:
##  Automatically tags all campaigns that have the word 'marca' in the campaign name with brand (=marca)
## 
## author: Dana Waidhas 
## created: 2024-03-20
## 

# Define the configurable parameters
SEP = '|'
TAG_LOCATION = 1  # Comes before the first separator

# Primary data source and columns
inputDf = dataSourceDict["1"]

# Define column names
RPT_COL_CAMPAIGN = 'Campaign'
RPT_COL_ACCOUNT = 'Account'
RPT_COL_BRAND_VS_NONBRAND = 'Brand vs NonBrand'

# Output columns and initial values
BULK_COL_ACCOUNT = 'Account'
BULK_COL_CAMPAIGN = 'Campaign'
BULK_COL_BRAND_VS_NONBRAND = 'Brand vs NonBrand'

# Function to extract brand from campaign name
def extract_tag_from_campaign_name(campaign_name, separator='|'):
    """
    Extracts the tag (Brand or NonBrand) from the campaign name based on specific keywords appearing before the separator.
    
    Args:
    campaign_name (str): The name of the campaign.
    separator (str): The separator used to split the campaign name.
    
    Returns:
    str or None: The extracted tag (Brand or NonBrand) if found, else None.
    """
    # Split the campaign name by the separator
    parts = campaign_name.split(separator)
    
    # Get the first part of the campaign name
    first_part = parts[TAG_LOCATION - 1].lower()  # Adjust index to zero-based
    
    # Check for keywords and return the corresponding tag
    if 'marca' in first_part:
        return 'Brand'
    elif 'curso' in first_part or 'generica' in first_part or 'oportunidade' in first_part:
        return 'NonBrand'
    else:
        return None

# Copy all input rows to output
outputDf = inputDf.copy()

# Iterate through all rows
for index, row in inputDf.iterrows():
    campaign_name = row[RPT_COL_CAMPAIGN]
    
    # Extract tag from campaign name
    brand = extract_tag_from_campaign_name(campaign_name, separator=SEP)
    
    # Print campaign and brand information
    print("Campaign [%s] => Brand [%s]" % (campaign_name, brand))
    
    # Update the output dataframe with the extracted tag
    outputDf.at[index, BULK_COL_BRAND_VS_NONBRAND] = brand

# Drop rows with NaN values in the 'Brand vs NonBrand' column
outputDf = outputDf.dropna(subset=[BULK_COL_BRAND_VS_NONBRAND])

# Display the resulting dataframe
if not outputDf.empty:
    print("outputDf", tableize(outputDf))
else:
    print("Empty outputDf")