File size: 9,308 Bytes
bb0bb89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1fa4303
bb0bb89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
import os
import io
import time
import json
import random
import tempfile
from datetime import datetime, timedelta

import pandas as pd
import numpy as np
import gradio as gr

try:
    import openai
    OPENAI_AVAILABLE = True
except Exception:
    OPENAI_AVAILABLE = False

OPENAI_API_KEY = os.getenv('OPENAI_API_KEY')
if OPENAI_AVAILABLE and OPENAI_API_KEY:
    openai.api_key = OPENAI_API_KEY

def generate_sample_csv(n=50):
    base_date = datetime.now() + timedelta(days=7)
    rows = []
    interests = ["Data Engineering", "Machine Learning", "Web Dev", "Cloud", "Product"]
    channels = ["Organic", "Ads", "Referral", "Partner", "Email Campaign"]
    for i in range(1, n + 1):
        name = f"User{i:03d}"
        email = f"user{i:03d}@example.com"
        phone = f"+91100000{i:04d}"[-13:]
        interest = random.choice(interests)
        channel = random.choice(channels)
        registered_at = (datetime.now() - timedelta(days=random.randint(0, 14))).strftime('%Y-%m-%d')
        rows.append({
            "id": i,
            "name": name,
            "email": email,
            "phone": phone,
            "interest": interest,
            "channel": channel,
            "registered_at": registered_at
        })
    df = pd.DataFrame(rows)

    tmpfile = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
    df.to_csv(tmpfile.name, index=False)
    tmpfile.close()

    return tmpfile.name

def load_leads_from_file(fileobj):
    if fileobj is None:
        return pd.DataFrame()
    try:
        df = pd.read_csv(fileobj)
    except Exception:
        fileobj.seek(0)
        df = pd.read_csv(io.StringIO(fileobj.read().decode('utf-8')))
    for col in ["name", "email", "phone", "interest", "registered_at"]:
        if col not in df.columns:
            df[col] = ""
    return df

def estimate_attendance_prob(df, event_date=None):
    df = df.copy()
    if event_date is None:
        event_date = datetime.now() + timedelta(days=7)
    else:
        if isinstance(event_date, str):
            event_date = datetime.fromisoformat(event_date)

    def channel_score(ch):
        ch = str(ch).lower()
        if 'ref' in ch: return 0.12
        if 'organic' in ch: return 0.08
        if 'partner' in ch: return 0.10
        if 'email' in ch: return 0.06
        return 0.03

    interest_map = {
        'Data Engineering': 0.12,
        'Machine Learning': 0.11,
        'Web Dev': 0.07,
        'Cloud': 0.09,
        'Product': 0.06
    }

    probs = []
    for _, r in df.iterrows():
        try:
            reg = datetime.fromisoformat(str(r.get('registered_at')))
        except Exception:
            reg = datetime.now()
        days_until = (event_date - reg).days
        if days_until <= 0:
            base = 0.25
        elif days_until <= 2:
            base = 0.22
        elif days_until <= 7:
            base = 0.18
        else:
            base = 0.12
        ch_boost = channel_score(r.get('channel', ''))
        interest_boost = interest_map.get(r.get('interest'), 0.05)
        noise = random.uniform(-0.03, 0.03)
        p = base + ch_boost + interest_boost + noise
        p = max(0.01, min(0.95, p))
        probs.append(round(p, 3))
    df['predicted_prob'] = probs
    return df

def generate_personalized_message(row, event_name="Scaler Live: Roadmap to Data Engineering", event_date=None, use_openai=False):
    if event_date is None:
        event_date = (datetime.now() + timedelta(days=7)).strftime('%b %d, %Y')

    name = row.get('name', 'there')
    interest = row.get('interest', '')
    prob = row.get('predicted_prob', None)

    if use_openai and OPENAI_AVAILABLE and OPENAI_API_KEY:
        prompt = f"Write a short personalized reminder message (1-2 sentences) for {name} who is interested in {interest} to attend the online event '{event_name}' on {event_date}. Make it friendly and include a single call-to-action 'Join here: <link>'."
        try:
            resp = openai.Completion.create(
                engine='text-davinci-003',
                prompt=prompt,
                max_tokens=80,
                temperature=0.7,
                n=1
            )
            return resp.choices[0].text.strip()
        except Exception:
            pass

    urgency = "Don't miss out!" if (prob is not None and prob < 0.25) else "Can't wait to see you there!"
    return f"Hi {name},\nWe have a short live session '{event_name}' on {event_date} that covers {interest} topics you care about. {urgency} Join here: <join-link>"

def batch_generate_messages(df, event_name, event_date, use_openai=False):
    df = df.copy()
    messages = []
    for _, r in df.iterrows():
        msg = generate_personalized_message(r, event_name=event_name, event_date=event_date, use_openai=use_openai)
        messages.append(msg)
    df['message'] = messages
    return df

def simulate_send_campaign(df, channel='email'):
    sent_rows = []
    opens = 0
    clicks = 0
    for _, r in df.iterrows():
        p = float(r.get('predicted_prob', 0.1))
        open_prob = min(0.9, 0.2 + p * 0.6)
        click_prob = min(0.8, 0.05 + p * 0.5)
        opened = random.random() < open_prob
        clicked = opened and (random.random() < click_prob)
        sent_rows.append({
            'id': r.get('id'),
            'name': r.get('name'),
            'email': r.get('email'),
            'phone': r.get('phone'),
            'predicted_prob': r.get('predicted_prob'),
            'opened': opened,
            'clicked': clicked,
            'message': r.get('message')
        })
        opens += int(opened)
        clicks += int(clicked)
    sent_df = pd.DataFrame(sent_rows)
    stats = {
        'total_sent': len(sent_df),
        'opens': int(opens),
        'clicks': int(clicks),
        'open_rate': round(opens / max(1, len(sent_df)), 3),
        'click_rate': round(clicks / max(1, len(sent_df)), 3)
    }
    out_path = '/mnt/data/simulated_sent_log.csv'
    try:
        sent_df.to_csv(out_path, index=False)
    except Exception:
        pass
    return stats, sent_df

def ui_generate_sample_csv(n=50):
    return generate_sample_csv(n)

def ui_load_and_preview(file):
    if file is None:
        return pd.DataFrame()
    df = load_leads_from_file(file)
    df = estimate_attendance_prob(df)
    return df

def ui_estimate_and_generate(df, event_name, event_date, use_openai=False):
    if isinstance(df, str):
        df = pd.read_csv(io.StringIO(df))
    if df is None or len(df) == 0:
        return pd.DataFrame(), "No leads provided"
    df = estimate_attendance_prob(df, event_date=event_date)
    df = batch_generate_messages(df, event_name, event_date, use_openai=use_openai)
    return df, f"Generated messages and probabilities for {len(df)} leads"

def ui_simulate_send(df):
    if isinstance(df, str):
        df = pd.read_csv(io.StringIO(df))
    stats, sent_df = simulate_send_campaign(df)
    return stats, sent_df

def ui_export_csv(df):
    if isinstance(df, str):
        df = pd.read_csv(io.StringIO(df))
    tmpfile = tempfile.NamedTemporaryFile(delete=False, suffix=".csv")
    df.to_csv(tmpfile.name, index=False)
    tmpfile.close()
    return tmpfile.name

with gr.Blocks(title="AI Conversion Automator - Scaler APM MVP") as demo:
    gr.Markdown("# AI Conversion Automator β€” Increase joining % for free live class")

    with gr.Tab("1. Sample CSV"):
        with gr.Row():
            n_samples = gr.Slider(minimum=10, maximum=500, value=50, label="Number of sample leads")
            gen_btn = gr.Button("Generate sample CSV")
        sample_download = gr.File()
        gen_btn.click(fn=ui_generate_sample_csv, inputs=[n_samples], outputs=[sample_download])

    with gr.Tab("2. Upload & Preview Leads"):
        uploader = gr.File(label="Upload leads CSV (columns: id,name,email,phone,interest,channel,registered_at)")
        preview = gr.Dataframe(headers=None, row_count=10)
        load_btn = gr.Button("Load & Preview")
        load_btn.click(fn=ui_load_and_preview, inputs=[uploader], outputs=[preview])

    with gr.Tab("3. Generate Messages & Predictions"):
        event_name = gr.Textbox(label="Event name", value="Roadmap to Data Engineering β€” Live Class")
        event_date = gr.Textbox(label="Event date (YYYY-MM-DD)", value=(datetime.now() + timedelta(days=7)).strftime('%Y-%m-%d'))
        use_openai = gr.Checkbox(label="Use OpenAI for message generation (requires OPENAI_API_KEY)", value=False)
        generate_btn = gr.Button("Generate Messages & Probabilities")
        generated_table = gr.Dataframe(headers=None, row_count=20)
        status_txt = gr.Textbox(label="Status")
        generate_btn.click(fn=ui_estimate_and_generate, inputs=[preview, event_name, event_date, use_openai], outputs=[generated_table, status_txt])

    with gr.Tab("4. Simulate Campaign"):
        simulate_btn = gr.Button("Simulate Send")
        sim_stats = gr.JSON()
        sim_table = gr.Dataframe(headers=None, row_count=20)
        simulate_btn.click(fn=ui_simulate_send, inputs=[generated_table], outputs=[sim_stats, sim_table])

    with gr.Tab("5. Export"):
        export_btn = gr.Button("Export CSV")
        download_file = gr.File()
        export_btn.click(fn=ui_export_csv, inputs=[generated_table], outputs=[download_file])


if __name__ == '__main__':
    demo.launch()