eda-tools-oyu 0.1.0__tar.gz

eda_tools_oyu-0.1.0/PKG-INFO

@@ -0,0 +1,8 @@
+Metadata-Version: 2.4
+Name: eda-tools-oyu
+Version: 0.1.0
+Description-Content-Type: text/markdown
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn

eda_tools_oyu-0.1.0/pyproject.toml

@@ -0,0 +1,10 @@
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "eda-tools-oyu"
+version = "0.1.0"
+readme = "README.md"
+dependencies = ["pandas", "numpy",
+                "matplotlib", "seaborn"]

eda_tools_oyu-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

eda_tools_oyu-0.1.0/src/core.py

@@ -0,0 +1,59 @@
+import numpy as np  # type: ignore
+import pandas as pd # type: ignore
+import matplotlib.pyplot as plt # type: ignore
+import seaborn as sns # type: ignore
+
+
+def basic_stats(x):
+    """Тоон массивын үндсэн статистик."""
+    x = np.array(x)
+    return {"n": len(x),
+            "mean": round(float(x.mean()), 2),
+            "median": float(np.median(x)),
+            "std": round(float(x.std(ddof=1)), 2),
+            "min": float(x.min()),
+            "max": float(x.max())}
+
+
+def iqr_outliers(x):
+    """1.5 x IQR дүрмээр outlier утгуудыг буцаана."""
+    x = np.array(x)
+    q1, q3 = np.percentile(x, [25, 75])
+    iqr = q3 - q1
+    return x[(x < q1 - 1.5 * iqr) | (x > q3 + 1.5 * iqr)]
+
+
+def missing_report(df):
+    """Багана бүрийн хоосон утгын тоо ба хувь."""
+    n = df.isnull().sum()
+    return pd.DataFrame({"missing": n, "percent": (n / len(df) * 100).round(1)})
+
+
+def group_rate(df, by, target):
+    """Бүлэг бүрийн хүний тоо ба target-ийн дундаж."""
+    return df.groupby(by)[target].agg(["count", "mean"]).round(2)
+
+
+def plot_hist(df, col):
+    """Histogram, дундаж ба медианы шугамтай."""
+    fig, ax = plt.subplots(figsize=(7, 4))
+    ax.hist(df[col], bins=30, edgecolor="white")
+    ax.axvline(df[col].mean(), color="orange", lw=4, label=f"дундаж = {df[col].mean():.1f}")
+    ax.axvline(df[col].median(), color="red", lw=2, ls="--", label=f"медиан = {df[col].median():.1f}")
+    ax.set_title(col); ax.legend()
+    plt.show()
+
+
+def plot_box(df, x, y):
+    """Бүлэг бүрийн тархалтыг boxplot-оор харьцуулна."""
+    sns.boxplot(data=df, x=x, y=y)
+    plt.title(f"{y} ба {x}")
+    plt.show()
+
+
+def plot_corr(df):
+    """Тоон багануудын корреляцийн heatmap."""
+    corr = df.select_dtypes("number").corr()
+    sns.heatmap(corr, annot=True, fmt=".2f", cmap="coolwarm", vmin=-1, vmax=1)
+    plt.title("Корреляц")
+    plt.show()

eda_tools_oyu-0.1.0/src/eda_tools_oyu.egg-info/PKG-INFO

@@ -0,0 +1,8 @@
+Metadata-Version: 2.4
+Name: eda-tools-oyu
+Version: 0.1.0
+Description-Content-Type: text/markdown
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: matplotlib
+Requires-Dist: seaborn

eda_tools_oyu-0.1.0/src/eda_tools_oyu.egg-info/SOURCES.txt

@@ -0,0 +1,7 @@
+pyproject.toml
+src/core.py
+src/eda_tools_oyu.egg-info/PKG-INFO
+src/eda_tools_oyu.egg-info/SOURCES.txt
+src/eda_tools_oyu.egg-info/dependency_links.txt
+src/eda_tools_oyu.egg-info/requires.txt
+src/eda_tools_oyu.egg-info/top_level.txt

eda_tools_oyu-0.1.0/src/eda_tools_oyu.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

eda_tools_oyu-0.1.0/src/eda_tools_oyu.egg-info/requires.txt

@@ -0,0 +1,4 @@
+pandas
+numpy
+matplotlib
+seaborn

eda_tools_oyu-0.1.0/src/eda_tools_oyu.egg-info/top_level.txt

@@ -0,0 +1 @@
+core