Update app.py

app.py

@@ -1,4 +1,425 @@
 import streamlit as st
+import numpy as np
+import plotly.figure_factory as ff
 
-x = st.slider('Select a value')
-st.write(x, 'squared is', x * x)
+import plotly.graph_objects as go
+import plotly.express as px
+
+
+import requests
+import json
+import pandas as pd
+import shutil
+import os
+from openai import AzureOpenAI
+import base64
+
+
+# st.page_link("report.py", label="Home", icon="🏠")
+# st.page_link("pages/page_1.py", label="Page 1", icon="1️⃣")
+# st.page_link("pages/page_2.py", label="Page 2", icon="2️⃣", disabled=True)
+
+ACCOUNT_ID = "act_416207949073936"
+PAGE_ID = "63257509478"
+OPENAI_API = os.getenv("OPENAI_API")
+ACCESS_TOKEN = os.getenv("ACCESS_TOKEN")
+BIG_DATASET = None
+
+ANALYSIS_TYPE = {
+    "OUTCOME_SALES": "ROAS",
+}
+
+API_BASE = 'https://bestever-vision.openai.azure.com/'
+DEPLOYMENT_NAME = 'vision'
+API_VERSION = '2023-12-01-preview' # this might change in the future
+API_URL = f"{API_BASE}openai/deployments/{DEPLOYMENT_NAME}/extensions"
+
+client = AzureOpenAI(
+    api_key=OPENAI_API,
+    api_version=API_VERSION,
+    base_url=API_URL,
+)
+
+def encode_image(image_path):
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+
+def call_gpt_vision(client, images_path, user_prompt):
+    """Call the GPT4 Vision API to generate tags."""
+    images_content = [
+        {
+            "type": "image_url",
+            "image_url": {
+                "url": f"data:image/jpeg;base64,{encode_image(image_path)}",
+            },
+        }
+        for image_path in images_path
+    ]
+    user_content = [
+        {"type": "text", "text": user_prompt},
+    ]
+    user_content += images_content
+    response = client.chat.completions.create(
+        model=DEPLOYMENT_NAME,
+        messages=[
+            {"role": "user", "content": user_content},
+        ],
+        max_tokens=2000,
+    )
+    return response
+
+
+def parse_tags_from_content(response):
+    """Parse the tags from the response."""
+    tags = []
+    content = response.choices[0].message.content
+    for full_tag in content.split("\n"):
+        splitted_fields = full_tag.split(":")
+        if len(splitted_fields) < 2:
+            continue
+        tag_name = splitted_fields[0]
+        tag_details = ":".join(splitted_fields[1:])
+        tag_element = {"name": tag_name, "metadata": {"details": tag_details}}
+        tags.append(tag_element)
+    return tags
+
+
+def get_campaigns(account_id):
+    url = f"{account_id}/insights"
+    params = {
+        "date_preset": "last_90d",
+        "fields": "campaign_id,campaign_name,impressions,spend,objective",
+        "level": "campaign",
+        "access_token": ACCESS_TOKEN,
+    }
+    return call_graph_api(url, params)
+
+
+def get_adsets(campaign_id):
+    url = f"{campaign_id}/insights"
+    params = {
+        "date_preset": "last_90d",
+        "fields": "adset_id,adset_name,impressions,spend",
+        "level": "adset",
+        "access_token": ACCESS_TOKEN,
+    }
+    return call_graph_api(url, params)
+
+
+def get_ads(adset_id):
+    url = f"{adset_id}/insights"
+    params = {
+        "date_preset": "last_90d",
+        "fields": "ad_name,ad_id,impressions,spend,video_play_actions,video_p25_watched_actions,video_p50_watched_actions,video_p75_watched_actions,video_p100_watched_actions,video_play_curve_actions,purchase_roas",
+        "breakdowns": "age,gender",
+        "limit": 1000,
+        "level": "ad",
+        "access_token": ACCESS_TOKEN,
+    }
+    return call_graph_api(url, params)
+
+
+def save_image_from_url(url, filename):
+    res = requests.get(url, stream = True)
+
+    if res.status_code == 200:
+        with open(filename,'wb') as f:
+            shutil.copyfileobj(res.raw, f)
+        return True
+    return False
+
+def get_creative_assets(ad_id):
+    # checking if the asset already exists
+    if os.path.exists(f'assets/{ad_id}.png') or os.path.exists(f'assets/{ad_id}.mp4') or os.path.exists(f'assets/{ad_id}.jpg'):
+        return
+    url = f"{ad_id}"
+    params = {
+        "fields": "creative{video_id,id,effective_object_story_id,image_url}",
+        "access_token": ACCESS_TOKEN,
+    }
+    creative = call_graph_api(url, params)["creative"]
+    saved = False
+    print("-" * 10)
+    if "video_id" in creative:
+        # download video
+        video_id = creative["video_id"]
+        video_url = f"{video_id}"
+        video_params = {
+            "fields": "source",
+            "access_token": ACCESS_TOKEN,
+        }
+        video_source = call_graph_api(video_url, video_params)["source"]
+        ext = video_source.split("?")[0].split(".")[-1]
+        if len(ext) > 4:
+            ext = "mp4"
+        saved = save_image_from_url(video_source, os.path.join("assets", f'{ad_id}.{ext}'))
+
+    elif "image_url" in creative:
+        image_url = creative["image_url"]
+        ext = image_url.split("?")[0].split(".")[-1]
+        if len(ext) > 4:
+            ext = "png"
+        saved = save_image_from_url(image_url, os.path.join("assets", f'{ad_id}.{ext}'))
+    
+    elif "effective_object_story_id" in creative:
+        object_story_url = creative["effective_object_story_id"]
+        object_story_params = {
+            "fields": "attachments",
+            "access_token": ACCESS_TOKEN,
+        }
+        attachments = call_graph_api(object_story_url, object_story_params)["attachments"]
+        if "media" in attachments:
+            media = attachments["media"]
+            if "source" in media or "video" in media:
+                video_url = media["video"]["source"]
+                ext = video_url.split("?")[0].split(".")[-1]
+                if len(ext) > 4:
+                    ext = "png"
+                saved = save_image_from_url(video_url, os.path.join("assets", f'{ad_id}.{ext}'))
+            elif "image" in media:
+                image_url = media["image"]["src"]
+                ext = image_url.split("?")[0].split(".")[-1]
+                if len(ext) > 4:
+                    ext = "mp4"
+                saved = save_image_from_url(image_url, os.path.join("assets", f'{ad_id}.{ext}'))
+
+    if not saved:
+        creative_url = f'{creative["id"]}'
+        creative_params = {
+            "fields": "thumbnail_url",
+            "access_token": ACCESS_TOKEN,
+            "thumbnail_width": 512,
+            "thumbnail_height": 512,
+        }
+        thumbnail_url = call_graph_api(creative_url, creative_params)["thumbnail_url"]
+        ext = thumbnail_url.split("?")[0].split(".")[-1]
+        if len(ext) > 4:
+            ext = "jpg"
+        saved = save_image_from_url(thumbnail_url, os.path.join("assets", f'{ad_id}.{ext}'))
+
+def call_graph_api(url, params):
+    base_url = "https://graph.facebook.com/v19.0/"
+    response = requests.get(base_url + url, params=params)
+    return json.loads(response.text)
+
+
+def top_n_ads(df, n=5):
+    ad_ids = df.head(n)["ad_id"].values
+    image_paths = []
+    for ad_id in ad_ids:
+        if os.path.exists(f'assets/{ad_id}.png'):
+            image_paths.append(f'assets/{ad_id}.png')
+        elif os.path.exists(f'assets/{ad_id}.mp4'):
+            image_paths.append(f'assets/{ad_id}.mp4')
+        elif os.path.exists(f'assets/{ad_id}.jpg'):
+            image_paths.append(f'assets/{ad_id}.jpg')
+    return image_paths
+
+
+def perform_analysis(df, objective):
+    # - TS to CTR ratio analysis
+    # - ROAS analysis (I will see the better metric here to use)
+    # - Video drop off analysis
+    if ANALYSIS_TYPE[objective] == "ROAS":
+        # 3 analysis:
+        # general
+        # male
+        # female
+
+        df_general = df.groupby(["ad_id"]).sum()
+        df_general = df_general.reset_index()
+        df_general["relative_roas"] = df_general["purchase_roas"] / df_general["spend"]
+        df_general = df_general.sort_values("relative_roas", ascending=False)
+        
+        image_paths = top_n_ads(df_general)
+        response = call_gpt_vision(client, image_paths, "You are a marketing analyst and your task is to find common features between the most performatives ads of the company. You are given the top 5 most perfomative ads, and we expect you to return 5 keywords and its explanation that defines what makes a good ad that show an excellent ROAS. Return it as a list of 5 concepts and its explanation, using the provided ads as example. Try to use nice categories to describe the features (you can use some names like `minimalist design`, `Clear message`, etc). Also, pay attention if the ads are mostly images or videos, this is important to say. The output MUST contain one concept per line. For each like, follow the structure: <concept>:<explanation>.")
+        image_winner_concepts = parse_tags_from_content(response)
+
+        response = call_gpt_vision(client, [], f"Following, you have the key features that makes an ad a performative ad. Your task is to group this information and summarize in a nice paragraph that will be presented to the marketing team. Be concise. Features:\n{image_winner_concepts}")
+        insights = response.choices[0].message.content
+
+        general_output = {"keywords": [concept["name"] for concept in image_winner_concepts], "insights": insights}
+
+        # Groupby ad_id and gender
+        df_male = df[df["gender"] == "male"].groupby(["ad_id"]).sum()
+        df_male = df_male.reset_index()
+        df_male["relative_roas"] = df_male["purchase_roas"] / df_male["spend"]
+        df_male = df_male.sort_values("relative_roas", ascending=False)
+        
+        image_paths = top_n_ads(df_male)
+        response = call_gpt_vision(client, image_paths, "You are a marketing analyst and your task is to find common features between the most performatives ads published to men. You are given the top 5 most perfomative ads, and we expect you to return 5 keywords and its explanation that defines what makes a good ad that show an excellent ROAS. Return it as a list of 5 concepts and its explanation, using the provided ads as example. Try to use nice categories to describe the features (you can use some names like `minimalist design`, `Clear message`, etc). Also, pay attention if the ads are mostly images or videos, this is important to say. The output MUST contain one concept per line. For each like, follow the structure: <concept>:<explanation>.")
+        image_winner_concepts = parse_tags_from_content(response)
+
+        response = call_gpt_vision(client, [], f"Following, you have the key features that makes an ad a performative ad. Your task is to group this information and summarize in a nice paragraph that will be presented to the marketing team. Be concise. Features:\n{image_winner_concepts}")
+        insights = response.choices[0].message.content
+
+        male_output = {"keywords": [concept["name"] for concept in image_winner_concepts], "insights": insights}
+
+
+        df_female = df[df["gender"] == "female"].groupby(["ad_id"]).sum()
+        df_female = df_female.reset_index()
+        df_female["relative_roas"] = df_female["purchase_roas"] / df_female["spend"]
+        df_female = df_female.sort_values("relative_roas", ascending=False)
+        
+        image_paths = top_n_ads(df_female)
+        response = call_gpt_vision(client, image_paths, "You are a marketing analyst and your task is to find common features between the most performatives ads published to women. You are given the top 5 most perfomative ads, and we expect you to return 5 keywords and its explanation that defines what makes a good ad that show an excellent ROAS. Return it as a list of 5 concepts and its explanation, using the provided ads as example. Try to use nice categories to describe the features (you can use some names like `minimalist design`, `Clear message`, etc). Also, pay attention if the ads are mostly images or videos, this is important to say. The output MUST contain one concept per line. For each like, follow the structure: <concept>:<explanation>.")
+        image_winner_concepts = parse_tags_from_content(response)
+
+        response = call_gpt_vision(client, [], f"Following, you have the key features that makes an ad a performative ad. Your task is to group this information and summarize in a nice paragraph that will be presented to the marketing team. Be concise. Features:\n{image_winner_concepts}")
+        insights = response.choices[0].message.content
+        female_output = {"keywords": [concept["name"] for concept in image_winner_concepts], "insights": insights}
+
+        return {
+            "General": general_output,
+            "Male":  male_output,
+            "Female": female_output,
+        }
+
+def format_adsets(campaign_id):
+    st_campaigns.empty()
+    adsets = get_adsets(campaign_id)
+    with st_adsets.container():
+        st.title("Adsets")
+        for adset in adsets["data"]:
+            with st.popover(adset["adset_name"]):
+                st.markdown("**Impressions**: " + str(adset["impressions"]))
+                st.markdown("**Total Spend**: US$" + str(adset["spend"]))
+                st.button(
+                    "View Ads",
+                    key=adset["adset_name"],
+                    on_click=format_ads,
+                    kwargs={"adset_id": adset["adset_id"]},
+                )
+
+
+def format_ads(adset_id):
+    st_adsets.empty()
+    BIG_DATASET = None
+    ads = get_ads(adset_id)
+    df_ads = pd.DataFrame(ads["data"])
+    options = ["gender"] #st.multiselect(
+    #     "Which breakdowns do you want to see?", ["gender", "age"], ["gender"]
+    # )
+    df_ads["spend"] = df_ads["spend"].astype(float)
+    df_ads["impressions"] = df_ads["impressions"].astype(float)
+    video_cols = ["video_play_actions","video_p25_watched_actions","video_p50_watched_actions","video_p75_watched_actions","video_p100_watched_actions"]
+    for col in video_cols:
+        if col in df_ads.columns:
+            df_ads[col] = df_ads[col].apply(lambda x: float(x[0].get("value", 0)) if isinstance(x, list) else 0)
+    
+    if "purchase_roas" in df_ads.columns:
+        df_ads["purchase_roas"] = df_ads["purchase_roas"].apply(lambda x: float(x[0].get("value", 0)) if isinstance(x, list) else 0)
+
+    if BIG_DATASET is None:
+        BIG_DATASET = df_ads
+    else:
+        BIG_DATASET = pd.concat([BIG_DATASET, df_ads])
+    BIG_DATASET.to_csv("big_dataset.csv")
+    with st_ads.container():
+        with st.expander("See analysis", expanded=False):
+            analysis = st.empty()
+
+        for i, ad in enumerate(df_ads["ad_id"].unique()):
+            get_creative_assets(ad)
+            ad_name = df_ads[df_ads["ad_id"] == ad]["ad_name"].values[0]
+            with st.popover(ad_name):
+                tab1, tab2, tab3 = st.tabs(["Creative", "Analytics", "Video Analysis"])
+                df_tmp = df_ads[df_ads["ad_id"] == ad]
+                with tab2:
+                    if len(options) >= 1:
+                        label = ["Total impressions"]
+                        source = []
+                        target = []
+                        value = []
+                        for option in options:
+                            df_g_tmp = df_tmp.groupby(option).sum()
+                            df_g_tmp = df_g_tmp.reset_index()
+                            for imp, v in df_g_tmp[["impressions", option]].values:
+                                label.append(v)
+                                source.append(0)
+                                target.append(len(label) - 1)
+                                value.append(imp)
+
+                        fig = go.Figure(
+                            data=[
+                                go.Sankey(
+                                    node=dict(
+                                        pad=15,
+                                        thickness=20,
+                                        line=dict(color="black", width=0.5),
+                                        label=label,
+                                        color="blue",
+                                    ),
+                                    link=dict(
+                                        source=source, target=target, value=value
+                                    ),
+                                )
+                            ]
+                        )
+                        fig.update_layout(title_text="Basic Sankey Diagram", font_size=10)
+                        st.plotly_chart(fig, use_container_width=True)
+
+                    if "purchase_roas" in df_tmp.columns:
+                        df_roas = df_tmp.groupby(options)[["spend","purchase_roas"]].sum().reset_index().sort_values("purchase_roas", ascending=False)
+                        print(df_roas)
+                        values = [str(v) for v in df_tmp[options].values]
+                        fig = go.Figure(data=[
+                            go.Bar(name='ROAS', x=values, y=df_roas["purchase_roas"]),
+                            go.Bar(name='Spend', x=values, y=df_roas["spend"])
+                        ])
+                        # Change the bar mode
+                        fig.update_layout(barmode='group')
+                        st.plotly_chart(fig, use_container_width=True)
+
+                with tab3:
+                    if "video_play_actions" in df_tmp.columns:
+                        values = df_ads[["ad_id","video_play_actions","video_p25_watched_actions","video_p50_watched_actions","video_p75_watched_actions","video_p100_watched_actions"]].groupby("ad_id").get_group(ad).sum().values[1:]
+                        labels = ["Total video plays","Video plays until 25%","Video plays until 50%","Video plays until 75%","Video plays until 100%"]
+                        print(values)
+                        if values[0] > 0:
+                            st.plotly_chart(create_video_plays_funnel(values, labels), use_container_width=True)
+                with tab1:
+                    if os.path.exists(f'assets/{ad}.png'):
+                        st.image(f'assets/{ad}.png', caption='Creative', use_column_width=True)
+                    elif os.path.exists(f'assets/{ad}.mp4'):
+                        st.video(f'assets/{ad}.mp4')
+                    elif os.path.exists(f'assets/{ad}.jpg'):
+                        st.image(f'assets/{ad}.jpg', caption='Creative', use_column_width=True)
+            
+        with analysis.container():
+            report = perform_analysis(df_tmp, "OUTCOME_SALES")
+            tabs = st.tabs(report.keys())
+            tabs_names = list(report.keys())
+            for i, tab in enumerate(tabs):
+                with tab:
+                    st.multiselect("", report[tabs_names[i]]["keywords"], report[tabs_names[i]]["keywords"], key=f"{ad}_{i}")
+                    st.write(report[tabs_names[i]]["insights"])
+
+def create_video_plays_funnel(funnel_data, funnel_title):
+    fig = go.Figure(go.Funnel(
+    y = funnel_title,
+    x = funnel_data))
+    return fig
+
+if "initiated" not in st.session_state:
+    st.session_state["initiated"] = False
+
+if not st.session_state["initiated"]:
+    st_campaigns = st.empty()
+    st_adsets = st.empty()
+    st_ads = st.empty()
+    st.session_state["initiated"] = True
+    with st_campaigns.container():
+        st.title("Campaigns")
+        for c in (get_campaigns(ACCOUNT_ID))["data"]:
+            with st.popover(c["campaign_name"]):
+                st.markdown("**Impressions**: " + str(c["impressions"]))
+                st.markdown("**Total Spend**: US$" + str(c["spend"]))
+                st.markdown("**Objective**: " + str(c["objective"]))
+                st.button(
+                    "View Adsets",
+                    key=c["campaign_name"],
+                    on_click=format_adsets,
+                    kwargs={"campaign_id": c["campaign_id"]},
+                )