File size: 3,421 Bytes
40084ed 2600c23 40084ed 2600c23 40084ed 2600c23 40084ed 2600c23 40084ed 2600c23 40084ed 2600c23 40084ed 2600c23 40084ed | 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 | import os
import pandas as pd
from rapidfuzz import process, fuzz
# ============================================================
# DATA LOCATION
# ============================================================
BASE_DIR = os.path.dirname(
os.path.dirname(
os.path.abspath(__file__)
)
)
PROVERB_FILE = os.path.join(
BASE_DIR,
"data",
"proverbs.csv"
)
# ============================================================
# LOAD PROVERBS
# ============================================================
def load_proverbs():
try:
df = pd.read_csv(
PROVERB_FILE,
encoding="utf-8"
)
df.columns = (
df.columns
.str.strip()
)
df.fillna("", inplace=True)
print("Proverbs loaded successfully")
print("Columns:", df.columns.tolist())
print("Records:", len(df))
return df
except Exception as e:
print(
f"Proverb loading error: {e}"
)
return pd.DataFrame()
# ============================================================
# GLOBAL DATAFRAME
# ============================================================
proverb_df = load_proverbs()
# ============================================================
# SEARCH PROVERB
# ============================================================
def search_proverb(text, df=None):
if df is None:
df = proverb_df
if df.empty:
return "Proverb database unavailable."
if not text:
return "Please enter a proverb or keyword."
query = text.strip()
if not query:
return "Please enter a proverb or keyword."
# ========================================================
# VERIFY REQUIRED COLUMNS
# ========================================================
required_columns = ["Kiembu", "English"]
for col in required_columns:
if col not in df.columns:
return (
f"Missing column '{col}' "
f"in proverbs.csv"
)
# ========================================================
# EXACT MATCH
# ========================================================
exact_match = df[
df["Kiembu"]
.astype(str)
.str.lower()
.str.strip()
== query.lower()
]
if not exact_match.empty:
proverb = exact_match.iloc[0]["Kiembu"]
meaning = exact_match.iloc[0]["English"]
return f"""
### Proverb Found
**Kiembu**
{proverb}
**English Meaning**
{meaning}
"""
# ========================================================
# FUZZY SEARCH
# ========================================================
choices = (
df["Kiembu"]
.astype(str)
.tolist()
)
best_match = process.extractOne(
query,
choices,
scorer=fuzz.WRatio
)
if not best_match:
return "No proverb found."
proverb = best_match[0]
score = best_match[1]
if score < 70:
return (
"No close proverb found.\n\n"
f"Best similarity score: {score}"
)
row = df[
df["Kiembu"]
.astype(str)
== proverb
]
if row.empty:
return "No proverb found."
meaning = row.iloc[0]["English"]
return f"""
### Suggested Proverb
**Kiembu**
{proverb}
**English Meaning**
{meaning}
""" |