querymind-cli 0.1.0__py3-none-any.whl

app/tools/join_resolver.py

@@ -0,0 +1,159 @@
+import pandas as pd
+
+
+class JoinResolver:
+    """
+    Detects when a query's metric and dimension columns exist in different
+    sheets (i.e. have no rows where both are non-null simultaneously),
+    finds the join key automatically, and produces a merged DataFrame
+    that the Analyzer can use normally.
+
+    Domain-agnostic: works purely from the loaded data structure.
+    No hardcoded column names or subject-matter assumptions.
+
+    Context keys read
+    -----------------
+    intent              – {"metric": str, "dimension": str, ...}
+    dataframe           – combined df (all sheets outer-joined)
+    sheet_dataframes    – dict[sheet_name -> DataFrame]
+    schema              – {"columns": [...]}
+
+    Context keys written
+    --------------------
+    dataframe           – replaced with joined df when a join is needed
+    schema              – updated to reflect joined df columns
+    join_resolved       – True if a join was performed
+    join_info           – dict with join details (for debugging / TUI display)
+    """
+
+    def run(self, context: dict) -> dict:
+        sheet_dfs = context.get("sheet_dataframes", {})
+
+        # Only relevant for multi-sheet Excel files
+        if len(sheet_dfs) < 2:
+            return context
+
+        intent = context.get("intent", {})
+        metric = intent.get("metric")
+        dimension = intent.get("dimension")
+
+        if not metric or not dimension:
+            return context
+
+        combined = context["dataframe"]
+
+        # ── Co-existence check ────────────────────────────────────────────
+        # The combined df outer-joins all sheets, so both columns may exist
+        # but have non-null values on completely different rows.
+        # If there are no rows where BOTH are non-null → cross-sheet join needed.
+        if metric in combined.columns and dimension in combined.columns:
+            both_valid = (combined[metric].notna() & combined[dimension].notna()).sum()
+            if both_valid > 0:
+                return context  # columns co-exist — no join needed
+
+        # ── Find which sheet owns each column ─────────────────────────────
+        metric_sheet = self._find_sheet(metric, sheet_dfs)
+        dimension_sheet = self._find_sheet(dimension, sheet_dfs)
+
+        if not metric_sheet:
+            return context  # let Analyzer produce a clear column-not-found error
+
+        if not dimension_sheet:
+            return context  # same
+
+        if metric_sheet == dimension_sheet:
+            # Both happen to be in the same sheet — use that df directly
+            context["dataframe"] = sheet_dfs[metric_sheet].copy()
+            context["schema"] = self._build_schema(context["dataframe"])
+            return context
+
+        # ── Find join key ─────────────────────────────────────────────────
+        join_key = self._find_join_key(
+            sheet_dfs[metric_sheet],
+            sheet_dfs[dimension_sheet],
+        )
+
+        if not join_key:
+            context["error"] = (
+                f"Cannot answer this query automatically.\n\n"
+                f"  '{metric}' lives in '{metric_sheet}' and "
+                f"'{dimension}' lives in '{dimension_sheet}', "
+                f"but these sheets share no common column to join on.\n\n"
+                f"  Try a query within a single sheet instead."
+            )
+            return context
+
+        # ── Perform the join ──────────────────────────────────────────────
+        try:
+            left_df = sheet_dfs[metric_sheet].copy()
+            right_df = sheet_dfs[dimension_sheet].copy()
+
+            # Only bring new columns from right (avoids _x/_y suffix collisions)
+            new_cols = [join_key] + [
+                c for c in right_df.columns if c not in left_df.columns
+            ]
+            right_df = right_df[new_cols]
+
+            joined = left_df.merge(right_df, on=join_key, how="left")
+
+            context["dataframe"] = joined
+            context["schema"] = self._build_schema(joined)
+            context["join_resolved"] = True
+            context["join_info"] = {
+                "metric_sheet": metric_sheet,
+                "dimension_sheet": dimension_sheet,
+                "join_key": join_key,
+                "joined_shape": joined.shape,
+            }
+
+            print(
+                f"JoinResolver: '{metric_sheet}' ⋈ '{dimension_sheet}' "
+                f"ON '{join_key}' → {joined.shape}"
+            )
+
+        except Exception as e:
+            context["error"] = f"Join failed: {e}"
+
+        return context
+
+    # ── Helpers ───────────────────────────────────────────────────────────
+
+    def _find_sheet(self, column: str, sheet_dfs: dict):
+        """Return the first sheet that contains column."""
+        for sheet, df in sheet_dfs.items():
+            if column in df.columns:
+                return sheet
+        return None
+
+    def _find_join_key(
+        self,
+        left_df: pd.DataFrame,
+        right_df: pd.DataFrame,
+    ):
+        """
+        Find the best shared column to join on.
+
+        Scoring: prefer columns where the right sheet is more lookup-like
+        (few unique values on right, many on left = classic FK→PK join).
+        Exclude obvious row-number columns.
+        """
+        shared = set(left_df.columns) & set(right_df.columns)
+
+        excluded_hints = {"row_id", "index", "unnamed"}
+        shared = {c for c in shared if not any(h in c.lower() for h in excluded_hints)}
+
+        if not shared:
+            return None
+
+        def score(col):
+            try:
+                return right_df[col].nunique() / max(left_df[col].nunique(), 1)
+            except Exception:
+                return 1.0
+
+        return sorted(shared, key=score)[0]
+
+    def _build_schema(self, df: pd.DataFrame) -> dict:
+        return {
+            "columns": [{"name": col, "type": str(df[col].dtype)} for col in df.columns]
+        }

app/tools/sql_writer.py

@@ -0,0 +1,37 @@
+class SQLWriter:
+    def run(self, context):
+        intent = context.get("intent")
+        schema = context.get("schema")
+
+        if not intent or not schema:
+            context["error"] = "Missing intent or schema"
+            return context
+
+        columns = [col["name"] for col in schema["columns"]]
+
+        metric = intent.get("metric")
+        dimension = intent.get("dimension")
+        analysis_type = intent.get("analysis_type")
+
+        # Safety check: ensure columns exist
+        if metric not in columns or dimension not in columns:
+            context["error"] = "Invalid columns in intent"
+            return context
+
+        try:
+            # Build SQL
+            sql = f"SELECT {dimension}, SUM({metric}) AS total_{metric} FROM data"
+
+            # GROUP BY
+            sql += f" GROUP BY {dimension}"
+
+            # ORDER BY (for comparison queries)
+            if analysis_type == "comparison":
+                sql += f" ORDER BY total_{metric} DESC"
+
+            context["sql_query"] = sql
+            return context
+
+        except Exception as e:
+            context["error"] = f"SQL generation failed: {str(e)}"
+            return context

querymind_cli-0.1.0.dist-info/METADATA

@@ -0,0 +1,139 @@
+Metadata-Version: 2.4
+Name: querymind-cli
+Version: 0.1.0
+Summary: CLI AI Data Analyst — query CSV and Excel files in plain English
+Author-email: Siddhesh <siddhesh.codemaster.github@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/SiddheshCodeMaster/QueryMind
+Project-URL: Repository, https://github.com/SiddheshCodeMaster/QueryMind
+Project-URL: Bug Tracker, https://github.com/SiddheshCodeMaster/QueryMind/issues
+Keywords: data analysis,cli,natural language,csv,excel,pandas,llm,ollama,terminal,data analytics
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Utilities
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=2.0
+Requires-Dist: rich>=13.0
+Requires-Dist: textual>=0.47
+Requires-Dist: requests>=2.31
+Requires-Dist: chardet>=5.0
+Requires-Dist: openpyxl>=3.1
+Requires-Dist: xlrd>=2.0
+Dynamic: license-file
+
+# 🧠 QueryMind
+
+**Ask questions about your data in plain English. No SQL. No code. Just a terminal.**
+
+QueryMind is a CLI data analyst that lets you load a CSV or Excel file and query it conversationally — right in your terminal.
+
+```
+>> top 5 regions by sales
+>> which month had the highest profit?
+>> average spend by payment method in ascending order
+>> show sales in sheet Orders by customer segment
+```
+
+---
+
+## Install
+
+```bash
+pip install querymind-cli
+```
+
+**Requirements:**
+- Python 3.10+
+- [Ollama](https://ollama.ai) (optional — enables LLM fallback for complex queries)
+
+If you want LLM support, install Ollama and pull the model:
+```bash
+ollama pull phi
+```
+
+---
+
+## Quickstart
+
+```bash
+querymind
+```
+
+You'll be prompted to:
+1. Enter a CSV or Excel file path
+2. Select sheets (Excel only)
+3. Map your metric and dimension columns
+4. Start asking questions
+
+---
+
+## What it can do
+
+| Query | What happens |
+|---|---|
+| `top 5 products by revenue` | Ranked bar chart in terminal |
+| `which region had lowest sales` | Ascending comparison with insight |
+| `average profit by category` | Mean aggregation per group |
+| `sales trend over time monthly` | Monthly groupby on datetime column |
+| `show sales in sheet Orders by region` | Sheet-scoped query |
+| `which manager had the most sales` | Cross-sheet join (Orders + Users) |
+| `sales by region in ascending order` | Explicit sort order |
+
+---
+
+## Supported file formats
+
+| Format | Extension |
+|---|---|
+| CSV | `.csv`, `.tsv` |
+| Excel | `.xlsx`, `.xls`, `.xlsm` |
+
+Auto-detects: encoding (UTF-8 BOM, latin-1), delimiter (comma, semicolon, tab, pipe), packed integer dates (DDMMYYYY, YYYYMMDD).
+
+---
+
+## How it works
+
+```
+Your query
+    ↓
+InputGuard       — blocks gibberish and sensitive input
+    ↓
+InterpreterAgent — rule-based intent extraction (fast, no LLM needed)
+    ↓
+LLMInterpreter   — Ollama fallback for complex queries (optional)
+    ↓
+JoinResolver     — auto-detects and performs cross-sheet joins
+    ↓
+Analyzer         — pandas groupby / aggregation
+    ↓
+InsightGenerator — formats result + ASCII bar chart
+```
+
+---
+
+## Beta
+
+QueryMind is in active development. If something breaks or a query gives a wrong answer, please [open an issue](https://github.com/SiddheshCodeMaster/QueryMind/issues) with:
+- Your query
+- The column names in your file (no need to share actual data)
+- The output you got
+
+This feedback directly shapes what gets fixed next.
+
+---
+
+## License
+
+MIT

querymind_cli-0.1.0.dist-info/RECORD

@@ -0,0 +1,43 @@
+app/agents/InterpreterAgent.py,sha256=VO-ibaWjFvuy-S06FMWZrHy6SLAukfQ6RHn-R_EvrzQ,17590
+app/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/agents/insights_generator.py,sha256=NS3vInyvHWKChPbwxXaUvc7VZpVhgBPnK_2iJIYtw-Y,5935
+app/agents/intent_corrector.py,sha256=hhT78H3Yg-RyRcnnmabM_wsLTP-YdNlkjxFrwFK_ras,2217
+app/agents/llm_intepreter.py,sha256=NeAWFCdtagCufbmVr_4h4Ujyp9HFfcxkcBUVs-3esLU,4440
+app/agents/narrator.py,sha256=6OT-XyKjkqson6GcjO-uGVTPdIiTWebpKLluRiWL-0w,707
+app/agents/planner.py,sha256=ENOw9XsjTRb-te_Wv7A37O4cRMUjvKMTAqdakYvoeY8,2352
+app/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/cli/main.py,sha256=tIkk2MaA4r2xxIGlTdB3Fqg9dHIh2A_i3QRMi8KzMbw,13718
+app/cli/tui_app.py,sha256=34SfvpPuHBduvARnEJo1LqvwWlD1Gupv4doEDrERC4Y,2975
+app/cli/ui.py,sha256=w066O0YJykmUNFDY0MJVEmIhMXirlvR-iFxR3gzuke8,525
+app/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/core/context.py,sha256=i1E8bY67WpySZ_FDZdn8LrNXVbe6FbAEB_TyS6HbeHw,282
+app/core/logger.py,sha256=Xy00yyxfTvJsjWkDQhPOWctWuv-xrpR5KLdyWqU7_0Y,95
+app/core/pipeline.py,sha256=4e8BnGRbNJO9jVlipTxfoTjnkOMD7jG9gbkFnamAJUA,13409
+app/data/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/data/schema_engine.py,sha256=QbpoADeGjKkZLWIjmuEREx1WwY1gBcMWE1eqXoJzKGo,497
+app/data/type_caster.py,sha256=rXMy4spsa8EMn7__Tn95RDt22x-lfC4l-Muy2sJ_oYs,4562
+app/data/connectors/csv_connector.py,sha256=tpA7bCucV_G48FBQbG_2YV3kqZsOkenQag0p9J5Z_0Y,3367
+app/data/connectors/excel_connector.py,sha256=BOk5g4W-A_KKocPxSHNPR157IASmHFUXiHI6EuAhuGg,2572
+app/data/connectors/no_sql_db_connector.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/data/connectors/sql_db_connector.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/executor/db_executor.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/executor/sheet_selector.py,sha256=X_4CXfNkgMzjJSIGkpKrvm4MTPGM52FZd52f7PKcoJA,4218
+app/llm/ollama_client.py,sha256=pTmwoTpIwqy1JFosjD7q6GZZ7Li7vcB7GlyhPBdMBzQ,1358
+app/prompts/interpreter_prompt.txt,sha256=uyg_1iXhmgvoV-MOSNaHNMWkt4SusOy5guxcys9zV3k,620
+app/security/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/security/input_guard.py,sha256=_zf6FeN_4dXmtHQsPg-OUN03ysndQTciElTXZ-V5680,2961
+app/security/schema_filter.py,sha256=jGPx557EsYM1fU4eqirdbreg6vEFRCHntJ4X97DJCjw,473
+app/tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/tests/llm_test.py,sha256=ci5tL4kTSF16e0ov6m5z_ZY_zTNDDMA6nDB5vE4xsP0,388
+app/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+app/tools/analyzer.py,sha256=nbdwaUcvSGSRYx5Okb-jGuoKq46XSrvxgX0j1VfyQwU,7083
+app/tools/join_resolver.py,sha256=lir29AZsPYU9_M7c_SI6HToNFsAwa8kKRV2hJS_2whM,6518
+app/tools/sql_writer.py,sha256=UdSJNtF380H9UXcH1DTebTFTTPgc2Uk7X48onPbDIIk,1206
+app/tools/validator.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+querymind_cli-0.1.0.dist-info/licenses/LICENSE,sha256=AGAfkJ3vPHAHt2b8yrK5Sz0YsbRAW7iRP4AoAiyVmLY,1094
+querymind_cli-0.1.0.dist-info/METADATA,sha256=w6-OY_U2rc_ke3sLr5yY8Uj2g97gRMCEBArgkPe3Djk,4028
+querymind_cli-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+querymind_cli-0.1.0.dist-info/entry_points.txt,sha256=zUoXxONuufqV4XVVZRIfNgJLbdgt4g8DVHJLR8TJdl8,48
+querymind_cli-0.1.0.dist-info/top_level.txt,sha256=io9g7LCbfmTG1SFKgEOGXmCFB9uMP2H5lerm0HiHWQE,4
+querymind_cli-0.1.0.dist-info/RECORD,,

querymind_cli-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

querymind_cli-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+querymind = app.cli.main:main

querymind_cli-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Siddhesh Shankar
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

querymind_cli-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+app