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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
## name: Dimension Tags from Campaign Name
## description: Extracts pacing dates and goal from campaign name
## author: 
## created: 2023-12-04
## 7/1 Updated version with CPM and MS for Social Campaigns 
## 6/27 Updated version w/o 'Target (Impr/Spend/Views)'

# Column Definitions
RPT_COL_CAMPAIGN = 'Campaign'
RPT_COL_ACCOUNT = 'Account'
RPT_COL_PACING_START_DATE = 'Pacing - Start Date'
RPT_COL_PACING_END_DATE = 'Pacing - End Date'
RPT_COL_GOAL = 'Goal'

# Function to convert date with enhanced logic to handle two-digit years
def convert_date(date_str):
    if date_str is None:
        return None
    try:
        # Try to parse date with four-digit year
        return datetime.datetime.strptime(date_str, '%m/%d/%Y').date()
    except ValueError:
        try:
            # Try to parse date with two-digit year
            return datetime.datetime.strptime(date_str, '%m/%d/%y').date()
        except ValueError:
            return None

# Function to extract information from the campaign name with enhanced logic
def extract_info_from_campaign_name_enhanced(campaign_name):
    # Updated date pattern to handle various delimiters and formats
    date_pattern = r'\(?(\d{1,2}/\d{1,2}/\d{2,4})[-\s_]+(\d{1,2}/\d{1,2}/\d{2,4})\)?'
    goal_pattern = r'\b(Search|RGD|SGD|SBD|CPM|MS)\b'
    
    date_match = re.search(date_pattern, campaign_name)
    goal_match = re.search(goal_pattern, campaign_name)
    
    start_date_str, end_date_str = (date_match.groups() if date_match else (None, None))
    goal_segment = goal_match.group(1) if goal_match else None
    
    if goal_segment == 'CPM':
        goal = 'CPM'
    elif goal_segment == 'MS':
        goal = 'MS'
    else:
        goal = 'CPM' if goal_segment in ['RGD', 'SGD', 'SBD'] else ''
    
    start_date = convert_date(start_date_str)
    end_date = convert_date(end_date_str)
    
    return start_date, end_date, goal

# Rename columns to match the script's expectations
inputDf.columns = ['Campaign', 'Account', 'Pacing - Start Date', 'Pacing - End Date', 'Goal', 'Unnamed', 'Target (Impr/Spend/Views)']

# Drop the 'Unnamed' column
inputDf.drop(columns=['Unnamed'], inplace=True)

# Clean any leading/trailing spaces in the column names
inputDf.columns = inputDf.columns.str.strip()

# Filter for rows where the Goal column is blank and create a copy to avoid SettingWithCopyWarning
inputDf_filtered = inputDf[inputDf[RPT_COL_GOAL].isna()].copy()

# Ensure that the campaign names are treated as strings to avoid TypeError
inputDf_filtered[RPT_COL_CAMPAIGN] = inputDf_filtered[RPT_COL_CAMPAIGN].astype(str)

# Adding columns for extracted information to inputDf_filtered
inputDf_filtered[RPT_COL_PACING_START_DATE] = np.nan
inputDf_filtered[RPT_COL_PACING_END_DATE] = np.nan
inputDf_filtered[RPT_COL_GOAL] = np.nan

# Process each row in inputDf_filtered to extract information
for index, row in inputDf_filtered.iterrows():
    start_date, end_date, goal = extract_info_from_campaign_name_enhanced(row[RPT_COL_CAMPAIGN])
    if start_date or end_date or goal:  # Include rows with any valid extracted information
        inputDf_filtered.loc[index, RPT_COL_PACING_START_DATE] = start_date
        inputDf_filtered.loc[index, RPT_COL_PACING_END_DATE] = end_date
        inputDf_filtered.loc[index, RPT_COL_GOAL] = goal

# Filter inputDf_filtered for rows with extracted information
filteredDf = inputDf_filtered.dropna(subset=[RPT_COL_GOAL])

# Define the columns to be included in the output DataFrame
cols = [
    RPT_COL_CAMPAIGN,
    RPT_COL_ACCOUNT,
    RPT_COL_PACING_START_DATE,
    RPT_COL_PACING_END_DATE,
    RPT_COL_GOAL
]

# Create output DataFrame with the selected columns
outputDf = filteredDf[cols].copy()

# Print the output DataFrame to check the extracted information
print("Output DataFrame with extracted information:")
print(outputDf)