Upload 7 files

src/.env

@@ -0,0 +1 @@
+GEMINI_API_KEY="AQ.Ab8RN6KA0xNgoncudDRxlsjRUe0RW15JwCoqCDJP4x38Vw8lCw"

src/cleaner.py

@@ -0,0 +1,25 @@
+import pandas as pd
+
+def clean_dataframe(df):
+
+    df = df.drop_duplicates()
+
+    for col in df.columns:
+
+        if df[col].dtype == "object":
+
+            df[col] = (
+                df[col]
+                .astype(str)
+                .str.strip()
+            )
+
+        if pd.api.types.is_numeric_dtype(
+            df[col]
+        ):
+
+            df[col] = df[col].fillna(
+                df[col].median()
+            )
+
+    return df

src/excel_reader.py

@@ -0,0 +1,11 @@
+import pandas as pd
+
+def read_file(file):
+
+    if file.name.endswith(".csv"):
+        return {"Sheet1": pd.read_csv(file)}
+
+    return pd.read_excel(
+        file,
+        sheet_name=None
+    )

src/gemini_agent.py

@@ -0,0 +1,28 @@
+import importlib
+import importlib.util
+import os
+
+package_name = "google.generativeai"
+if importlib.util.find_spec(package_name) is None:
+    raise ImportError(
+        "Package 'google.generativeai' not found. Install it with 'pip install google-generative-ai'"
+    )
+genai = importlib.import_module(package_name)
+
+genai.configure(
+    api_key=os.getenv(
+        "GEMINI_API_KEY"
+    )
+)
+
+model = genai.GenerativeModel(
+    "gemini-2.5-flash"
+)
+
+def get_suggestions(summary):
+
+    response = model.generate_content(
+        summary
+    )
+
+    return response.text

src/outlier.py

@@ -0,0 +1,29 @@
+def detect_outliers(df):
+
+    result = {}
+
+    for col in df.select_dtypes(
+        include="number"
+    ).columns:
+
+        q1 = df[col].quantile(0.25)
+
+        q3 = df[col].quantile(0.75)
+
+        iqr = q3 - q1
+
+        lower = q1 - 1.5 * iqr
+
+        upper = q3 + 1.5 * iqr
+
+        count = len(
+            df[
+                (df[col] < lower)
+                |
+                (df[col] > upper)
+            ]
+        )
+
+        result[col] = count
+
+    return result

src/profiler.py

@@ -0,0 +1,17 @@
+def profile_dataframe(df):
+
+    profile = {}
+
+    profile["rows"] = len(df)
+
+    profile["columns"] = len(df.columns)
+
+    profile["missing"] = (
+        df.isnull().sum().sum()
+    )
+
+    profile["duplicates"] = (
+        df.duplicated().sum()
+    )
+
+    return profile

src/reporter.py

@@ -0,0 +1,24 @@
+def create_report(
+    profile,
+    outliers
+):
+
+    report = f"""
+
+Rows:
+{profile['rows']}
+
+Columns:
+{profile['columns']}
+
+Missing:
+{profile['missing']}
+
+Duplicates:
+{profile['duplicates']}
+
+Outliers:
+{outliers}
+"""
+
+    return report