File size: 4,944 Bytes
928f866
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr
import pandas as pd
import joblib
from nltk.stem import WordNetLemmatizer
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.metrics import classification_report
from sklearn.compose import ColumnTransformer
from sklearn.impute import SimpleImputer
from textblob import TextBlob
import nltk
nltk.download('punkt')
nltk.download('wordnet')
import numpy as np

# Load pre-trained models and preprocessor objects
model = joblib.load('pet_adoption.pkl')
preprocessor = joblib.load('preprocessor.pkl')

# Lemmatizer for text preprocessing
lemmatizer = WordNetLemmatizer()

# Function to preprocess text input
def preprocess_text(text):
    text = text.lower()
    text = text.replace('[^\w\s]','',regex=True)
    text = text.replace('\s+',' ',regex=True)
    text = text.replace('\n',' ',regex=True)
    text = text.replace('\d+',' ',regex=True)
    stop_words = set(stopwords.words('english'))
    words = nltk.word_tokenize(text)
    words = [word for word in words if word not in stop_words]
 
    # Lemmatization
    words = [lemmatizer.lemmatize(word) for word in words]
    # Join processed words
    return ' '.join(words)


# Duygu analizi fonksiyonu
def analyze_sentiment(description):
    analysis = TextBlob(description)
    # Sentiment.polarity değeri -1 ile 1 arasında değişir: -1 negatif, 0 nötr, 1 pozitif
    return analysis.sentiment.polarity

def sentiment_to_adoption_speed(sentiment):
    if sentiment > 0.2:
        return 2  # Yüksek olumlu duygu
    elif sentiment < -0.2:
        return 0  # Yüksek olumsuz duygu
    else:
        return 1  # Nötr veya orta duygu



# Gradio arayüzü için girdi alanları ve işlemler
def predict_adoption_speed(age, breed1, breed2, gender, color1, color2, color3,
                           maturity_size, fur_length, vaccinated, dewormed,
                           sterilized, health, quantity, fee, state, video_amt,
                           photo_amt, description):
    
    # Convert input into DataFrame format
    data = pd.DataFrame({
        'Age': [age],
        'Breed1': [breed1],
        'Breed2': [breed2],
        'Gender': [gender],
        'Color1': [color1],
        'Color2': [color2],
        'Color3': [color3],
        'MaturitySize': [maturity_size],
        'FurLength': [fur_length],
        'Vaccinated': [vaccinated],
        'Dewormed': [dewormed],
        'Sterilized': [sterilized],
        'Health': [health],
        'Quantity': [quantity],
        'Fee': [fee],
        'State': [state],
        'VideoAmt': [video_amt],
        'PhotoAmt': [photo_amt],
        'sentiments': [sentiments]
    })
    
    # Separate numerical and categorical columns
    num_columns = ['Age', 'Quantity', 'Fee', 'VideoAmt', 'PhotoAmt']
    cat_columns = ['Breed1', 'Breed2', 'Gender', 'Color1', 'Color2', 'Color3',
                   'MaturitySize', 'FurLength', 'Vaccinated', 'Dewormed',
                   'Sterilized', 'Health', 'State']
    
    # Preprocess numerical and categorical data
    processed_data = preprocessor.transform(data)
    
    # Convert description text to sentiments
    cleaned_description = preprocess_text(description)
    sentiment = analyze_sentiment(cleaned_description)
    sentiments = sentiment_to_adoption_speed(sentiment)  # Placeholder for sentiment analysis
    
    # Make prediction
    prediction = model.predict(processed_data)
    
    # Return prediction result
    return int(prediction[0])

# Gradio arayüzünü oluşturma

# Define Gradio Interface
iface = gr.Interface(
    fn=predict_adoption_speed, 
    inputs=[
        gr.Slider(minimum=0, maximum=20, label="Age"),
        gr.Number(label="Breed1"),
        gr.Number(label="Breed2"),
        gr.Dropdown(choices=[0, 1, 2], label="Gender"),
        gr.Dropdown(choices=[1, 2, 3, 4, 5, 6, 7], label="Color1"),
        gr.Dropdown(choices=[0, 1, 2, 3, 4, 5, 6, 7], label="Color2"),
        gr.Dropdown(choices=[0, 1, 2, 3, 4, 5, 6, 7], label="Color3"),
        gr.Dropdown(choices=[0, 1, 2, 3], label="MaturitySize"),
        gr.Dropdown(choices=[1, 2, 3], label="FurLength"),
        gr.Dropdown(choices=[0, 1], label="Vaccinated"),
        gr.Dropdown(choices=[0, 1], label="Dewormed"),
        gr.Dropdown(choices=[0, 1], label="Sterilized"),
        gr.Dropdown(choices=[0, 1], label="Health"),
        gr.Number(label="Quantity"),
        gr.Number(label="Fee"),
        gr.Dropdown(choices=[41324, 41325, 41326, 41327, 41330, 41332, 41335, 41336, 41342, 41345, 41361, 41367, 41401, 41415, 41452], label="State"),
        gr.Slider(minimum=0, maximum=10, label="VideoAmt"),
        gr.Slider(minimum=0, maximum=10, label="PhotoAmt"),
        gr.Textbox(label="Description", placeholder="Enter pet description...")
    ],
    outputs=gr.Textbox(label="Predicted Adoption Speed")
)

# Launch Gradio Interface
iface.launch(share=True)