hackathon code for the category and ranking

app.py

@@ -17,6 +17,9 @@ from src.text_content import (
 from src.utils import add_latlng_col, init_map, parse_gg_sheet, is_request_in_list, parse_json_file
 from src.map_utils import get_legend_macro
 from src.dataframes import display_dataframe
+from src.filter.filter import add_category
+from src.filter.filter import HelpCategory
+from src.ranking.ranking import sort_request
 
 TOKEN = os.environ.get("HF_TOKEN", None)
 VERIFIED_REQUESTS_URL = (
@@ -131,6 +134,7 @@ show_embed_code()
 show_dataframes_metrics(len_requests, len_interventions, len_solved_verified_requests)
 
 # Verified Requests table
+verified_df = add_category(df)
 st.divider()
 st.subheader("📝 **Table of verified requests / جدول الطلبات المؤكدة**")
 drop_cols = [
@@ -147,6 +151,20 @@ display_dataframe(
     verified_df, drop_cols, VERIFIED_REQUESTS_URL, search_id=True, for_help_requests=True, show_link=False
 )
 
+# Requests table aggregate
+st.subheader("📝 **Table of aggragate")
+aggregate = aggregate_locations(verified_df)
+display_dataframe(
+    aggregate, [], VERIFIED_REQUESTS_URL, search_id=True, for_help_requests=True, show_link=False
+)
+
+# Requests table shelter
+st.subheader("📝 **Table of shelter request")
+house_request = verified_df[verified_df['Help Details'] == HelpCategory.HOUSE]
+display_dataframe(
+    house_request, drop_cols, VERIFIED_REQUESTS_URL, search_id=True, for_help_requests=True, show_link=False
+)
+
 # Requests table
 st.divider()
 st.subheader("📝 **Table of requests / جدول الطلبات**")
@@ -161,6 +179,10 @@ drop_cols = [
 ]
 display_dataframe(filtered_df, drop_cols, REQUESTS_URL, search_id=True, for_help_requests=True)
 
+st.subheader("📝 **Table of sorted requests / جدول الطلبات**")
+sorted_request = sort_request(filtered_df)
+display_dataframe(sorted_request, drop_cols, REQUESTS_URL, search_id=True, for_help_requests=True)
+
 # Interventions table
 st.divider()
 st.subheader("📝 **Table of interventions / جدول التدخلات**")

src/filter/const.py

@@ -0,0 +1,45 @@
+PHRASE_NO_PROBLEMS = ['got food',
+                      'got food and clothes',
+                     'got food and covers']
+
+KEYS_HOUSE = [
+    "shelters",
+    "mattresses",
+    "pillows",
+    "blankets",
+    "shelter",
+    "tentes",
+    "housing",
+    "couvertures",
+    "tents",
+    "covers",
+    "sdader",
+    "housing_shelter",
+]
+KEYS_FOOD = [
+    "groceries",
+    "nouriture",
+    "food",
+    "water",
+    "gaz",
+    "dishes",
+    "oil",
+    "sugar",
+    "tea",
+    "hungry",
+]
+KEYS_CLOTHES = [
+    "clothes",
+    "clothing",
+    "hygiene",
+]
+KEYS_MEDICAL = [
+    "betadine",
+    "medical",
+    "diabetics",
+    "medicaments",
+    "diabetes",
+    "doliprane",
+    "vitamines",
+    "drugs",
+]

src/filter/filter.py

@@ -0,0 +1,116 @@
+from const import KEYS_HOUSE, KEYS_FOOD, KEYS_CLOTHES, KEYS_MEDICAL
+
+import nltk
+from nltk.stem import WordNetLemmatizer
+
+DEGREE_SCORE = {'High': 9, 'Medium': 3, 'Low': 1}
+
+nltk.download('wordnet')
+nltk.download('omw-1.4')
+lemmatizer = WordNetLemmatizer()
+
+lemmatize_house = [lemmatizer.lemmatize(word) for word in KEYS_HOUSE]
+lemmatize_food = [lemmatizer.lemmatize(word) for word in KEYS_FOOD]
+lemmatize_clothes = [lemmatizer.lemmatize(word) for word in KEYS_CLOTHES]
+lemmatize_medical = [lemmatizer.lemmatize(word) for word in KEYS_MEDICAL]
+
+
+
+
+
+from typing import List
+from enum import Enum
+
+
+class HelpCategory(Enum):
+    HOUSE = 'house'
+    FOOD = 'food'
+    CLOTHES = 'clothes'
+    MEDICAL = 'medical'
+    UNKNOW = 'unknow'
+
+
+def to_category(text: str) -> List[HelpCategory]:
+    if text in PHRASE_NO_PROBLEMS:
+        return []
+
+    words = text.split()
+    categories = []
+    for word in words:
+        if word in KEYS_HOUSE:
+            categories.append(HelpCategory.HOUSE)
+        elif word in KEYS_FOOD:
+            categories.append(HelpCategory.FOOD)
+        if word in KEYS_CLOTHES:
+            categories.append(HelpCategory.CLOTHES)
+        if word in KEYS_MEDICAL:
+            categories.append(HelpCategory.MEDICAL)
+        if lemmatizer.lemmatize(word) in lemmatize_house:
+            categories.append(HelpCategory.HOUSE)
+        if lemmatizer.lemmatize(word) in lemmatize_food:
+            categories.append(HelpCategory.FOOD)
+        if lemmatizer.lemmatize(word) in lemmatize_clothes:
+            categories.append(HelpCategory.CLOTHES)
+        if lemmatizer.lemmatize(word) in lemmatize_medical:
+            categories.append(HelpCategory.MEDICAL)
+    if len(categories) == 0:
+        categories = [HelpCategory.UNKNOW]
+    return categories
+
+
+def clean(text: str) -> str:
+    text = text.replace('Housing/Shelter', 'housing_shelter')
+    text = text.replace('/', ',')
+    text = text.lower()
+    text = text.strip()
+    return text
+
+
+def to_list(text: str) -> List[str]:
+    helps = text.split(',')
+    helps = [help_string.replace('.', ' ').strip() for help_string in helps]
+    return helps
+
+
+def help_text_to_help_category(helps: List[str]) -> List[str]:
+    all_categories = set()
+    for help_string in helps:
+        categories = to_category(help_string)
+        all_categories.update(categories)
+    return list(all_categories)
+
+
+
+
+
+
+def aggregate_degree(degrees):
+    total_score = sum([DEGREE_SCORE[degree] for degree in degrees])
+    if total_score >= 9:
+        return 'High'
+    if total_score >= 3:
+        return 'Medium'
+    else:
+        return 'Low'
+
+def add_category(df):
+    df['help_category'] = df['Help Details'].apply(clean).apply(to_list).apply(help_text_to_help_category)
+    return df
+
+
+def aggregate_locations(df):
+    flatten_list = lambda lst: [item for sublist in lst for item in sublist]
+    need = df.groupby('Location Details')['help_category'].apply(list).apply(flatten_list).apply(lambda x: list(set(x)))
+
+    emergency_degree = df.groupby('Location Details')['Emergency Degree'].apply(list).apply(aggregate_degree)
+
+    result = pd.merge(need, emergency_degree, left_index=True, right_index=True)
+    return result
+
+
+
+
+
+def filter_category(category:HelpCategory, request:pd.DataFrame)-> pd.DataFrame:
+    in_category = request['help_category'].apply(lambda x : category in x)
+    return request[in_category]

src/ranking/ranking.py

@@ -0,0 +1,91 @@
+import datetime
+
+def calculate_score(row):
+    current_time = datetime.datetime.now()
+    delta = current_time - row['Horodateur']
+    base_score = delta.total_seconds() / 60
+
+    text_score = get_text_score(row)
+
+    temp_score = get_score_temp(row)
+
+    return base_score + text_score + temp_score
+
+def get_temp(lat, lon):
+  url = f'https://api.openweathermap.org/data/2.5/forecast?lat={lat}&lon={lon}&appid={API_KEY}'
+
+  response = requests.get(url)
+
+  if response.status_code == 200:
+      data = response.json()
+      temp = sum([single_point['main']['temp_min'] for single_point in data['list']])/40
+  else:
+      print(f'Error: Unable to fetch weather data. Status code: {response.status_code}')
+  return temp
+
+NEED_COL =  'ما هي احتياجاتك؟ (أضفها إذا لم يتم ذكرها)'
+COOR_COL = 'هل يمكنك تقديم الإحداثيات الدقيقة للموقع؟ (ادا كنت لا توجد بعين المكان) متلاً \n31.01837503440344, -6.781405948842175'
+
+def get_text_score(row):
+    score = 0
+
+    need = row[NEED_COL]
+    needs = need.split(' ')
+    if 'وماء' in needs:#water
+      score += 500
+    if 'طعام' in needs:#food
+      score += 500
+    if 'مساعدة طبية' in needs: #medical
+        score += 1000
+    if 'إغاثة' in needs:#secours
+      score+=800
+    if 'لنقود' in needs: #secours
+      score += 800
+    if 'الخيام' in needs: #tent
+      score += 500
+    if 'ولملابس' in needs:#clothes
+      score += 250
+    if 'الأغطية' in needs: #covers
+      score += 250
+    if 'أفرشة' in needs: #matress
+      score+=100
+
+    return score
+
+def get_score_temp(row):
+    score = 0
+    need = row[NEED_COL]
+    needs = need.split(' ')
+    # tent, clothes or cover
+    if ('الخيام' not in needs) and ('ولملابس' not in needs) and ('الأغطية' not in needs):
+      return score
+
+
+    lat, lon = row[COOR_COL].split(',')
+    lon = lon.strip()
+    lat = lat.strip()
+
+    average_temp = get_temp(lat, lon)
+    if average_temp < 283:
+        score += 1000
+    if average_temp < 273:
+        score += 1000
+    return score
+
+def sort_request(requests):
+
+    current_time = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
+    requests['Horodateur'].fillna(current_time, inplace=True)
+
+    scores = []
+    for index, row in requests.iterrows():
+        scores.append(calculate_score(row))
+
+    requests['score'] = scores
+
+    requests = requests.sort_values(by='score', ascending=False)
+
+    return requests
+
+
+