radwaamr1 commited on
Commit
28ccc4e
·
verified ·
1 Parent(s): 736b1db

Upload 9 files

Browse files
Dockerfile ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.11-slim
2
+
3
+ RUN apt-get update && apt-get install -y --no-install-recommends \
4
+ libgomp1 \
5
+ && rm -rf /var/lib/apt/lists/*
6
+
7
+ WORKDIR /app
8
+
9
+ COPY requirements.txt /app/requirements.txt
10
+ RUN pip install --no-cache-dir -r requirements.txt
11
+
12
+ COPY . /app
13
+
14
+ ENV PORT=7860
15
+ EXPOSE 7860
16
+
17
+ CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "7860"]
api/feature_engineering.py ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import pandas as pd
2
+ import numpy as np
3
+
4
+ def feature_engineering(input_df: pd.DataFrame) -> pd.DataFrame:
5
+ # Get season
6
+ def get_season(month):
7
+ if month in [12, 1, 2]:
8
+ return 'Winter'
9
+ elif month in [3, 4, 5]:
10
+ return 'Spring'
11
+ elif month in [6, 7, 8]:
12
+ return 'Summer'
13
+ else:
14
+ return 'Autumn'
15
+
16
+ input_df['season'] = input_df['month'].apply(get_season)
17
+
18
+ # Soil ratios
19
+ input_df['soil_total'] = input_df['sand'] + input_df['silt'] + input_df['clay']
20
+ input_df['soil_total'] = input_df['soil_total'].replace(0, np.nan)
21
+ input_df['sand_ratio'] = input_df['sand'] / input_df['soil_total']
22
+ input_df['silt_ratio'] = input_df['silt'] / input_df['soil_total']
23
+ input_df['clay_ratio'] = input_df['clay'] / input_df['soil_total']
24
+ input_df = input_df.drop(columns=['soil_total'])
25
+
26
+ # Combined feature
27
+ input_df['soc_cec'] = input_df['soc'] * input_df['cec']
28
+
29
+ return input_df
api/main.py ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # main.py
2
+ from fastapi import FastAPI, HTTPException
3
+ from pydantic import BaseModel
4
+ import pandas as pd
5
+ import numpy as np
6
+ import joblib, json, os
7
+ from math import radians, cos, sin, asin, sqrt
8
+
9
+ # =========================
10
+ # تحميل الموديل والـ artifacts
11
+ # =========================
12
+ MODEL_DIR = os.path.join(os.path.dirname(__file__), "..", "models")
13
+ MODEL_PATH = os.path.join(MODEL_DIR, "model.pkl")
14
+ PREPROCESSOR_PATH = os.path.join(MODEL_DIR, "preprocessor.pkl")
15
+ FEATURES_PATH = os.path.join(MODEL_DIR, "feature_names.json")
16
+
17
+ model = joblib.load(MODEL_PATH)
18
+ preprocessor = joblib.load(PREPROCESSOR_PATH)
19
+ with open(FEATURES_PATH) as f:
20
+ feature_names = json.load(f)
21
+
22
+ # =========================
23
+ # تحميل البيانات من CSV
24
+ # =========================
25
+ DATA_PATH = os.path.join(os.path.dirname(__file__), "..", "data", "features_data.csv")
26
+ features_df = pd.read_csv(DATA_PATH)
27
+
28
+ # =========================
29
+ # Feature Engineering
30
+ # =========================
31
+ def get_season(month: int) -> str:
32
+ if month in [12, 1, 2]:
33
+ return "Winter"
34
+ elif month in [3, 4, 5]:
35
+ return "Spring"
36
+ elif month in [6, 7, 8]:
37
+ return "Summer"
38
+ return "Autumn"
39
+
40
+ def feature_engineering(df: pd.DataFrame) -> pd.DataFrame:
41
+ df = df.copy()
42
+ df["season"] = df["month"].apply(get_season)
43
+
44
+ soil_total = df[["sand", "silt", "clay"]].sum(axis=1).replace(0, np.nan)
45
+ df["sand_ratio"] = (df["sand"] / soil_total).fillna(0.0)
46
+ df["silt_ratio"] = (df["silt"] / soil_total).fillna(0.0)
47
+ df["clay_ratio"] = (df["clay"] / soil_total).fillna(0.0)
48
+
49
+ df["soc_cec"] = df["soc"] * df["cec"]
50
+
51
+ return df
52
+
53
+ # =========================
54
+ # Input Schema
55
+ # =========================
56
+ class MapClick(BaseModel):
57
+ lat: float
58
+ lon: float
59
+
60
+ # =========================
61
+ # Helpers
62
+ # =========================
63
+ def haversine(lat1, lon1, lat2, lon2):
64
+ """حساب المسافة بين نقطتين (كم)"""
65
+ R = 6371.0
66
+ dlat = radians(lat2 - lat1)
67
+ dlon = radians(lon2 - lon1)
68
+ a = sin(dlat/2)**2 + cos(radians(lat1)) * cos(radians(lat2)) * sin(dlon/2)**2
69
+ c = 2 * asin(sqrt(a))
70
+ return R * c
71
+
72
+ def fetch_nearest_features(lat: float, lon: float, max_km=15):
73
+ """إرجاع أقرب نقطة من CSV"""
74
+ best = None
75
+ best_dist = 1e9
76
+
77
+ for _, row in features_df.iterrows():
78
+ d = haversine(lat, lon, row["latitude"], row["longitude"])
79
+ if d < best_dist:
80
+ best_dist = d
81
+ best = row.to_dict()
82
+ best["distance_km"] = d
83
+
84
+ if best and best_dist <= max_km:
85
+ return best
86
+ return None
87
+
88
+ def classify_desertification(ndvi: float) -> str:
89
+ if ndvi < 0.2:
90
+ return "شديد"
91
+ elif ndvi < 0.5:
92
+ return "متوسط"
93
+ return "منخفض"
94
+
95
+ # =========================
96
+ # توصيات ديناميكية
97
+ # =========================
98
+ def recommend_actions(severity: str, row: dict) -> list:
99
+ recs = []
100
+
101
+ if severity == "شديد":
102
+ recs.extend([
103
+ "التشجير وزراعة أحزمة خضراء",
104
+ "استخدام تقنيات حصاد المياه",
105
+ "منع الرعي الجائر وتنظيمه",
106
+ "تطبيق أنظمة ري حديثة (تنقيط/رش)"
107
+ ])
108
+ elif severity == "متوسط":
109
+ recs.extend([
110
+ "إدارة التربة وتحسين خصوبتها (إضافة مواد عضوية)",
111
+ "تنويع المحاصيل واستخدام محاصيل تغطية",
112
+ "تحسين ممارسات الري",
113
+ "الحد من إزالة الغطاء النباتي"
114
+ ])
115
+ else: # منخفض
116
+ recs.extend([
117
+ "المحافظة على الغطاء النباتي الحالي",
118
+ "المتابعة والرصد الدوري للتغيرات",
119
+ "التوسع في الزراعة المستدامة",
120
+ "التوعية المجتمعية لمنع الممارسات الضارة"
121
+ ])
122
+
123
+ # توصيات إضافية مبنية على الـ features
124
+ rainfall = row.get("tp_m", 0)
125
+ temp = row.get("t2m_c", 0)
126
+ sand_ratio = row.get("sand_ratio", 0)
127
+ clay_ratio = row.get("clay_ratio", 0)
128
+ soc_cec = row.get("soc_cec", 0)
129
+
130
+ if rainfall > 200 and sand_ratio > 0.6 and severity == "منخفض":
131
+ recs.append("تشجيع الزراعات الاقتصادية سريعة النمو لاستغلال الموارد المائية")
132
+
133
+ if rainfall < 50 and clay_ratio > 0.4 and severity != "منخفض":
134
+ recs.append("إنشاء سدود صغيرة أو خزانات لتخزين مياه الأمطار")
135
+
136
+ if temp > 35 and severity == "شديد":
137
+ recs.append("زراعة محاصيل مقاومة للجفاف والحرارة (مثل الشعير والدخن)")
138
+
139
+ if sand_ratio > 0.7:
140
+ recs.append("إضافة مواد عضوية أو طينية للتربة الرملية لزيادة قدرتها على الاحتفاظ بالماء")
141
+
142
+ if clay_ratio > 0.5:
143
+ recs.append("تجهيز أنظمة صرف زراعي لمنع تملح التربة الثقيلة")
144
+
145
+ if soc_cec < 0.2 and severity != "منخفض":
146
+ recs.append("إضافة محسنات للتربة (كمبوست/سماد عضوي) لرفع خصوبة التربة")
147
+
148
+ return recs
149
+
150
+ # =========================
151
+ # FastAPI app
152
+ # =========================
153
+ app = FastAPI()
154
+
155
+ @app.post("/predict-by-location")
156
+ def predict_by_location(click: MapClick):
157
+ try:
158
+ # 1. دور على أقرب نقطة من CSV
159
+ row = fetch_nearest_features(click.lat, click.lon, max_km=15)
160
+ if not row:
161
+ raise HTTPException(status_code=404, detail="لا توجد بيانات قريبة لهذه الإحداثيات")
162
+
163
+ # 2. حوّل النقطة DataFrame
164
+ df = pd.DataFrame([row])
165
+
166
+ # 3. Feature engineering
167
+ df = feature_engineering(df)
168
+
169
+ # 4. تأكد إن الأعمدة مرتبة حسب feature_names
170
+ df = df[feature_names]
171
+
172
+ # 5. Prediction
173
+ X_trans = preprocessor.transform(df)
174
+ ndvi_pred = float(model.predict(X_trans)[0])
175
+
176
+ # 6. تقييم التصحر + توصيات
177
+ severity = classify_desertification(ndvi_pred)
178
+ recs = recommend_actions(severity, df.iloc[0].to_dict())
179
+
180
+ return {
181
+ "clicked_point": {"lat": click.lat, "lon": click.lon},
182
+ "nearest_data_point": {
183
+ "lat": row["latitude"],
184
+ "lon": row["longitude"],
185
+ "distance_km": round(row["distance_km"], 2)
186
+ },
187
+ "predicted_ndvi": round(ndvi_pred, 3),
188
+ "desertification_level": severity,
189
+ "recommendations": recs
190
+ }
191
+
192
+ except Exception as e:
193
+ raise HTTPException(status_code=500, detail=str(e))
data/features_data.csv ADDED
The diff for this file is too large to render. See raw diff
 
models/feature_names.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["longitude", "latitude", "year", "month", "area", "t2m_c", "td2m_c", "rh_pct", "tp_m", "ssrd_jm2", "LC_Type1", "sand", "silt", "clay", "soc", "ph", "bdod", "cec", "POP", "season", "sand_ratio", "silt_ratio", "clay_ratio", "soc_cec"]
models/model.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a593035e1a75aefdd28cbdbecebe1a6a583d32345ff98b48f27856bd275c165d
3
+ size 158170789
models/preprocessor.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db331fab9ee29069314601a54db2460d5a573bb6b7cf5f29920c9f69db45ec90
3
+ size 4494
models/remodel.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
requirements.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ fastapi==0.111.0
2
+ uvicorn[standard]==0.30.1
3
+ pandas==2.2.2
4
+ numpy==1.26.4
5
+ lightgbm==4.3.0
6
+ joblib==1.4.2
7
+ pydantic==2.8.2
8
+ python-dotenv==1.0.1
9
+ scikit-learn==1.5.1