zaturn 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

zaturn/config.py

@@ -62,6 +62,9 @@ for s in source_list:
     elif source.startswith("mysql+pymysql://"):
         source_type = 'mysql'
         source_name = source.split('/')[-1].split('?')[0]
+    elif source.startswith('clickhouse://'):
+        source_type = 'clickhouse'
+        source_name = source.split('/')[-1].split('?')[0]
     elif source.endswith(".duckdb"):
         source_type = "duckdb"
         source_name = source.split('/')[-1].split('.')[0]

zaturn/core.py

@@ -62,7 +62,7 @@ def _list_tables(source_id: str):
                     if col.startswith("Tables_in_"):
                         return result[col].to_list()
                 
-            case "duckdb" | "csv" | "parquet":
+            case "duckdb" | "csv" | "parquet" | "clickhouse":
                 result = query_utils.execute_query(source, "SHOW TABLES")
                 return result['name'].to_list()
 
@@ -96,7 +96,7 @@ def describe_table(source_id: str, table_name: str) -> str:
                 )
                 return result.to_markdown(index=False)
                 
-            case "mysql" | "duckdb" | "csv" | "parquet":
+            case "mysql" | "duckdb" | "csv" | "parquet" | "clickhouse":
                 result = query_utils.execute_query(source,
                     f"DESCRIBE {table_name};"
                 )

zaturn/query_utils.py

@@ -1,3 +1,4 @@
+import clickhouse_connect
 import duckdb
 import numpy as np
 import os
@@ -46,6 +47,11 @@ def execute_query(source: dict, query: str):
                     result = conn.execute(sqlalchemy.text(query))
                     return pd.DataFrame(result)
 
+        case "clickhouse":
+            client = clickhouse_connect.get_client(dsn=url)
+            client.query('SET readonly=1;')
+            return client.query_df(query, use_extended_dtypes=False)
+
         case "duckdb":
             conn = duckdb.connect(url, read_only=True)
             return conn.execute(query).df()

zaturn/visualizations.py

@@ -1,69 +1,23 @@
 from fastmcp import FastMCP, Image
 import math
-import matplotlib.pyplot as plt
 import os
-import seaborn as sns
+import plotly.express as px
 import time
 from typing import Any, Union, Optional
 from zaturn import config, query_utils
 
-sns.set_theme()
-sns.set_style('ticks')
 
 mcp = FastMCP("Zaturn Visualizations")
 
 
-def _plot_to_image(plot) -> Union[str, Image]:
-    figure = plot.get_figure()
+def _fig_to_image(fig) -> Union[str, Image]:
     filepath = os.path.join(config.VISUALS_DIR, str(int(time.time())) + '.png')
-    figure.savefig(filepath, bbox_inches='tight')
-    plt.clf()
+    fig.write_image(filepath)
     if config.RETURN_IMAGES:
         return Image(path=filepath)
     else:
         return filepath
-
-
-def _fix_x_labels(plot, labels):
-    max_label_length = max(list(labels.map(lambda x: len(str(x)))))
-
-    LABEL_HIDE_FACTOR = 1
-    if len(labels) > 20:
-        LABEL_HIDE_FACTOR = math.ceil(len(labels)/20)
-
-    labels_to_show = list(labels)
-    ticks = list(plot.get_xticks()) 
-    if LABEL_HIDE_FACTOR > 1:
-        ticks = ticks[::LABEL_HIDE_FACTOR]
-        labels_to_show = labels_to_show[::LABEL_HIDE_FACTOR]
-            
-    plot.set_xticks(ticks, labels_to_show)
-    cutoff = 2 # for rotation
-    
-    if max_label_length >= 12:
-        cutoff = 3
-    elif max_label_length >= 10:
-        cutoff = 4
-    elif max_label_length >= 8:
-        cutoff = 5
-    elif max_label_length >= 7:
-        cutoff = 5
-    elif max_label_length >= 6:
-        cutoff = 6
-    elif max_label_length >= 5:
-        cutoff = 7
-    elif max_label_length >= 4:
-        cutoff = 9
-    elif max_label_length >= 3:
-        cutoff = 13
-    else:
-        cutoff = 15
-    
-    if len(labels)>cutoff:
-        plot.set_xticklabels(plot.get_xticklabels(), rotation=-45, ha='left', va='top')
-    
-    return plot
-
+        
 
 # Relationships
 
@@ -72,7 +26,7 @@ def scatter_plot(
     query_id: str,
     x: str,
     y: str,
-    hue: str = None
+    color: str = None
     ):
     """
     Make a scatter plot with the dataframe obtained from running SQL Query against source
@@ -81,12 +35,12 @@ def scatter_plot(
         query_id: Previously run query to use for plotting
         x: Column name from SQL result to use for x-axis
         y: Column name from SQL result to use for y-axis
-        hue: Optional String; Column name from SQL result to use for coloring the points  
+        color: Optional; column name from SQL result to use for coloring the points, with color representing another dimension
     """
     df = query_utils.load_query(query_id)
-    plot = sns.scatterplot(df, x=x, y=y, hue=hue)
-    plot = _fix_x_labels(plot, df[x])
-    return _plot_to_image(plot)
+    fig = px.scatter(df, x=x, y=y, color=color)
+    fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+    return _fig_to_image(fig)
 
 
 @mcp.tool()
@@ -94,7 +48,7 @@ def line_plot(
     query_id: str,
     x: str,
     y: str,
-    hue: str = None
+    color: str = None
     ):
     """
     Make a line plot with the dataframe obtained from running SQL Query against source
@@ -102,12 +56,12 @@ def line_plot(
         query_id: Previously run query to use for plotting
         x: Column name from SQL result to use for x-axis
         y: Column name from SQL result to use for y-axis
-        hue: Optional; column name from SQL result to use for drawing multiple colored lines
+        color: Optional; column name from SQL result to use for drawing multiple colored lines representing another dimension
     """
     df = query_utils.load_query(query_id)
-    plot = sns.lineplot(df, x=x, y=y, hue=hue)
-    plot = _fix_x_labels(plot, df[x])
-    return _plot_to_image(plot)
+    fig = px.line(df, x=x, y=y, color=color)
+    fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+    return _fig_to_image(fig)
 
 
 # Distributions
@@ -116,21 +70,21 @@ def line_plot(
 def histogram(
     query_id: str,
     column: str,
-    hue: str = None,
-    bins: int = None
+    color: str = None,
+    nbins: int = None
     ):
     """
     Make a histogram with a column of the dataframe obtained from running SQL Query against source
     Args:
         query_id: Previously run query to use for plotting
         column: Column name from SQL result to use for the histogram
-        hue: Optional; column name from SQL result to use for drawing multiple colored histograms
-        bins: Optional; number of bins
+        color: Optional; column name from SQL result to use for drawing multiple colored histograms representing another dimension
+        nbins: Optional; number of bins
     """
     df = query_utils.load_query(query_id)
-    plot = sns.histplot(df, x=column, hue=hue, bins=bins)
-    return _plot_to_image(plot)
-
+    fig = px.histogram(df, x=column, color=color, nbins=nbins)
+    fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+    return _fig_to_image(fig)
 
 # Categorical
 
@@ -139,8 +93,7 @@ def strip_plot(
     query_id: str,
     x: str,
     y: str = None,
-    hue: str = None,
-    legend: bool = False
+    color: str = None
     ):
     """
     Make a strip plot with the dataframe obtained from running SQL Query against source
@@ -148,34 +101,33 @@ def strip_plot(
         query_id: Previously run query to use for plotting
         x: Column name from SQL result to use for x axis
         y: Optional; column name from SQL result to use for y axis
-        hue: Optional; column name from SQL result to use for coloring the points
-        legend: Whether to draw a legend for the hue
+        color: Optional column name from SQL result to show multiple colored strips representing another dimension
     """
     df = query_utils.load_query(query_id)
-    plot = sns.stripplot(df, x=x, y=y, hue=hue, legend=legend)
-    plot = _fix_x_labels(plot, df[x])
-    return _plot_to_image(plot)
+    fig = px.strip(df, x=x, y=y, color=color)
+    fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+    return _fig_to_image(fig)
 
 
 @mcp.tool()
 def box_plot(
     query_id: str,
-    x: str,
-    y: str = None,
-    hue: str = None
+    y: str,
+    x: str = None,
+    color: str = None
     ):
     """
     Make a box plot with the dataframe obtained from running SQL Query against source
     Args:
         query_id: Previously run query to use for plotting
-        x: Column name from SQL result to use for x axis
-        y: Optional; column name from SQL result to use for y axis
-        hue: Optional column name from SQL result to use for coloring the points
+        y: Column name from SQL result to use for y axis
+        x: Optional; Column name from SQL result to use for x axis
+        color: Optional column name from SQL result to show multiple colored bars representing another dimension
     """
     df = query_utils.load_query(query_id)
-    plot = sns.boxplot(df, x=x, y=y, hue=hue)
-    plot = _fix_x_labels(plot, df[x])
-    return _plot_to_image(plot)
+    fig = px.box(df, x=x, y=y, color=color)
+    fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+    return _fig_to_image(fig)
 
 
 @mcp.tool()
@@ -183,8 +135,8 @@ def bar_plot(
     query_id: str,
     x: str,
     y: str = None,
-    hue: str = None,
-    orient: str = 'v'
+    color: str = None,
+    orientation: str = 'v'
     ):
     """
     Make a bar plot with the dataframe obtained from running SQL Query against source
@@ -192,12 +144,12 @@ def bar_plot(
         query_id: Previously run query to use for plotting
         x: Column name from SQL result to use for x axis
         y: Optional; column name from SQL result to use for y axis
-        hue: Optional column name from SQL result to use for coloring the bars
-        orient: Orientation of the box plot, use 'v' for vertical and 'h' for horizontal
+        color: Optional column name from SQL result to use as a 3rd dimension by splitting each bar into colored sections
+        orientation: Orientation of the box plot, use 'v' for vertical (default) and 'h' for horizontal. Be mindful of choosing the correct X and Y columns as per orientation
     """
     df = query_utils.load_query(query_id)
-    plot = sns.barplot(df, x=x, y=y, hue=hue, orient=orient)
-    plot = _fix_x_labels(plot, df[x])
-    return _plot_to_image(plot)
+    fig = px.bar(df, x=x, y=y, color=color, orientation=orientation)
+    fig.update_xaxes(autotickangles=[0, 45, 60, 90])
+    return _fig_to_image(fig)
 
 

{zaturn-0.1.4.dist-info → zaturn-0.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: zaturn
-Version: 0.1.4
+Version: 0.1.6
 Summary: AI Data Analysis MCP
 Author-email: Karthik Devan <krtdvn@gmail.com>
 Maintainer-email: Karthik Devan <krtdvn@gmail.com>
@@ -9,11 +9,14 @@ Project-URL: Issues, https://github.com/kdqed/zaturn/issues
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: clickhouse-connect>=0.8.17
 Requires-Dist: cryptography>=44.0.2
 Requires-Dist: duckdb>=1.2.1
 Requires-Dist: fastmcp>=0.4.1
+Requires-Dist: kaleido==0.2.1
 Requires-Dist: pandas>=2.2.3
 Requires-Dist: platformdirs>=4.3.7
+Requires-Dist: plotly[express]>=6.0.1
 Requires-Dist: psycopg2-binary>=2.9.10
 Requires-Dist: pyarrow>=19.0.1
 Requires-Dist: pymysql>=1.1.1
@@ -54,7 +57,7 @@ https://github.com/user-attachments/assets/d42dc433-e5ec-4b3e-bef0-5cfc097396ab
 
 ### Multiple Data Sources 
 Zaturn can currently connect to the following data sources: 
-- SQL Databases: PostgreSQL, SQLite, DuckDB, MySQL
+- SQL Databases: PostgreSQL, SQLite, DuckDB, MySQL, ClickHouse
 - Files: CSV, Parquet
 
 Connectors for more data sources are being added.
@@ -103,6 +106,7 @@ OR add a `sources.txt` to the Zaturn config directory:
 ```
 postgresql://username:password@host:port/dbname
 mysql+pymysql://username:password@host:3306/dbname
+clickhouse://username:password@host:port/dbname
 sqlite:////full/path/to/sample_dbs/northwind.db
 /full/path/to/sample_dbs/titanic.parquet
 /full/path/to/sample_dbs/ny_aq.csv
@@ -158,11 +162,20 @@ Analyst:
 ```
 - A native notebook interface 
 
-## Support And Feedback
+## Help And Feedback
 
 [Raise an issue](https://github.com/kdqed/zaturn/issues) or [join the Discord](https://discord.gg/K8mECeVzpQ).
 
 
+## Support The Project
+
+If you find Zaturn useful, please support this project by:
+- Starring the Project
+- Spreading the word
+- [Pledging $9/month on Patreon](https://www.patreon.com/kdqed?utm_medium=github&utm_source=join_link&utm_campaign=creatorshare_creator&utm_content=copyLink)
+
+Your support will enable me to dedicate more of my time to Zaturn.
+
 ## Example Dataset Credits
 
 The [pokemon dataset compiled by Sarah Taha and PokéAPI](https://www.kaggle.com/datasets/sarahtaha/1025-pokemon) has been included under the [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license for demonstration purposes.

zaturn-0.1.6.dist-info/RECORD

@@ -0,0 +1,12 @@
+zaturn/__init__.py,sha256=v4t5fkRuIJFE-SBxCa5pBjZv0EoC0eWK75nU9iaa7Rg,267
+zaturn/config.py,sha256=V0sqe72zCLyHVJyH27vOR401hA7NnRhkfaJlIeyNoXo,3359
+zaturn/core.py,sha256=hASmXF6iMQA5M62tf94YjE5D3Rja9Vj5-8zMVKQ_tOY,4671
+zaturn/query_utils.py,sha256=zXy8-eDpqpehgdHBs0zjLPfpLDsbF4xtiCEU1dE0xms,3028
+zaturn/visualizations.py,sha256=0ON70D_mK4o0oyfEKqAhr2jkKWz_5-kNKkD6_TGBR9k,5014
+zaturn/example_data/all_pokemon_data.csv,sha256=SUlGHHWbehuLg-ch1YUrQ6-xBtqHGw6rIkyn70fAgCk,130893
+zaturn-0.1.6.dist-info/licenses/LICENSE,sha256=mZSuFlbEBZGl0-8ULRMLdRDbhau5hrWRNQOjytYeaug,1070
+zaturn-0.1.6.dist-info/METADATA,sha256=tO7Fc7dIV_YumwTavFxKWQMGEitbDBE82zDv1J_vEVw,7179
+zaturn-0.1.6.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+zaturn-0.1.6.dist-info/entry_points.txt,sha256=N1UZC2zvod92_Brs4A2xZiAnt-iGLBNryglXfwhxfj4,43
+zaturn-0.1.6.dist-info/top_level.txt,sha256=KLUnwQwVZkfd5YCnnqR35MOOs8KLhanPGelvmRo2MVA,7
+zaturn-0.1.6.dist-info/RECORD,,

{zaturn-0.1.4.dist-info → zaturn-0.1.6.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.0)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

zaturn-0.1.4.dist-info/RECORD

@@ -1,12 +0,0 @@
-zaturn/__init__.py,sha256=v4t5fkRuIJFE-SBxCa5pBjZv0EoC0eWK75nU9iaa7Rg,267
-zaturn/config.py,sha256=gF5M6Agmixw2A4vpWqIF3ICVnClPeASA51dhp1bkk04,3221
-zaturn/core.py,sha256=9zcKb0FbkgGkDtWfBA6_O5NQf6GVKG69HrqOr5nhsLU,4641
-zaturn/query_utils.py,sha256=zyQjcRnPKGHZdf0XHzQeMxHw9vieZIwXhBbVGP87ml4,2801
-zaturn/visualizations.py,sha256=4RA4FytYNPiBdMyIqlw3dfjH7flT2Nz6ncVoVoIqPEA,5883
-zaturn/example_data/all_pokemon_data.csv,sha256=SUlGHHWbehuLg-ch1YUrQ6-xBtqHGw6rIkyn70fAgCk,130893
-zaturn-0.1.4.dist-info/licenses/LICENSE,sha256=mZSuFlbEBZGl0-8ULRMLdRDbhau5hrWRNQOjytYeaug,1070
-zaturn-0.1.4.dist-info/METADATA,sha256=VPtw2YcLYUz54oLKX72sCjzImF7xiqrM65e2u1j2-EE,6658
-zaturn-0.1.4.dist-info/WHEEL,sha256=pxyMxgL8-pra_rKaQ4drOZAegBVuX-G_4nRHjjgWbmo,91
-zaturn-0.1.4.dist-info/entry_points.txt,sha256=N1UZC2zvod92_Brs4A2xZiAnt-iGLBNryglXfwhxfj4,43
-zaturn-0.1.4.dist-info/top_level.txt,sha256=KLUnwQwVZkfd5YCnnqR35MOOs8KLhanPGelvmRo2MVA,7
-zaturn-0.1.4.dist-info/RECORD,,