sklip 0.4.0__py3-none-any.whl → 0.5.0__py3-none-any.whl

sklip/__init__.py

@@ -1,5 +1,5 @@
 from .core import s,ClusterKMeans,figsize,x
-__version__ = "0.4.0"
+__version__ = "0.5.0"
 __all__ = ['s','ClusterKMeans', 'figsize','x']
 
 s(1)

sklip/core.py

@@ -1,26 +1,123 @@
 import pyperclip
 
 SNIPPETS = {
-    1: "import 4333432numpy as np \n import pandas as pd \n import folium \n import seaborn as sns \n import matplotlib.pyplot as plt",
-    2: "import pandas as pd",
-    3: "import matplotlib.pyplot as plt",
-    4: "from sklearn.cluster import KMeans",
-    5: "from sklearn.decomposition import PCA",
-    6: "from sklearn.metrics import silhouette_score",
-    7: "from sklearn.cluster import AgglomerativeClustering",
-    8: "from sklearn.cluster import SpectralClustering",
-    9: "from scipy.cluster.hierarchy import dendrogram, linkage",
-    10: "import seaborn as sns",
-    11: "warnings.filterwarnings('ignore')",
-    12: "X = np.random.randn(100, 2)",
-    13: "kmeans = KMeans(n_clusters=3, random_state=42)",
-    14: "labels = kmeans.fit_predict(X)",
-    15: "pca = PCA(n_components=2)",
-    16: "plt.figure(figsize=(10, 7))",
-    17: "df = pd.read_csv('data.csv')",
-    18: "from sklearn.metrics import calinski_harabasz_score",
-    19: "import scipy.cluster.hierarchy as shc",
-    20: "np.random.seed(42)"
+    1: "import 4333432numpy as np \nimport pandas as pd \nimport folium \nimport seaborn as sns \nimport matplotlib.pyplot as plt",
+    2: """# Статистический анализ числовых колонок
+    numeric_columns = df.select_dtypes(include='number').columns
+    for col in numeric_columns:
+        print(f"{col}:")
+        print(f"  Медиана: {df[col].median():.2f}")
+        print(f"  Среднее: {df[col].mean():.2f}")
+        print(f"  Стандартное отклонение: {df[col].std():.2f}")
+        print(f"  Асимметрия: {df[col].skew():.2f}")
+        print(f"  Эксцесс: {df[col].kurtosis():.2f}")
+        print(f"  Минимум: {df[col].min():.2f}")
+        print(f"  Максимум: {df[col].max():.2f}")
+        print()""",
+    3: """from statsmodels.graphics.gofplots import qqplot
+from matplotlib import pyplot
+qqplot(df.step_frequency, line='s')
+pyplot.show""",
+    4: """from scipy.stats import shapiro
+from scipy.stats import  normaltest
+shapiro(df.step_frequency)""",
+    5: """df['datetime'] = pd.to_datetime(df['datetime'])
+df['hour'] =df['datetime'].dt.hour
+df['time_of_day'] = pd.cut(df['hour'],bins = [0,6,12,18,24],labels=['Ночь','Утро','День','Вечер'],right=False)
+""",
+    6: """plt.figure(figsize=(15,10))
+sns.heatmap(corr_matrix,annot=True)
+corr_matrix = dfcor.corr()""",
+    7: """lan = df['latitude'].mean()
+lon = df['longitude'].mean()
+
+m = folium.Map(location=[lan,lon],zoom_start=18)
+
+
+
+for idx,row in df.iterrows():
+    folium.CircleMarker(row[['latitude','longitude']].values,
+    color='red',radius = 3, fill = True ).add_to(m)
+m""",
+    8: """ if 'datetime' not in df.columns or df['datetime'].isnull().all():
+        df['datetime'] = pd.date_range('2026-01-01', periods=len(df), freq='1min')
+    else:
+        df['datetime'] = pd.to_datetime(df['datetime'], errors='coerce').fillna(
+            pd.Timestamp('2026-01-01')
+        )
+           if 'latitude' not in df: df['latitude'] = 51.26 + np.random.normal(0, 0.01, len(df))
+    if 'longitude' not in df: df['longitude'] = 10.86 + np.random.normal(0, 0.01, len(df))
+    if 'speed' not in df: df['speed'] = np.random.normal(4, 1, len(df)).clip(1, 8)
+    
+    numeric = ['latitude', 'longitude', 'speed', 'elevation']
+    avail_num = [col for col in numeric if col in df.columns]
+     scaler = StandardScaler()
+    knn = KNNImputer(n_neighbors=5, weights='distance')
+    
+    df_num = df[avail_num].fillna(0)
+    df_scaled = scaler.fit_transform(df_num)
+    df_filled = knn.fit_transform(df_scaled)
+    df[avail_num] = scaler.inverse_transform(df_filled)
+      df['step_frequency'] = np.clip(df['speed'] / 3.6 / 0.75 * 60, 60, 140)
+        bins = [0, 500, 1500, 3000, float('inf')]
+    labels = ['лес', 'холмы', 'горы', 'альпы']
+    df['terrain_type'] = pd.cut(df['elevation'], bins=bins, labels=labels)
+        """,
+
+    9: """from sklearn import metrics
+from sklearn.cluster import AgglomerativeClustering
+from sklearn.cluster import KMeans
+from sklearn.cluster import SpectralClustering
+import scipy.cluster.hierarchy as shc
+from scipy.cluster.hierarchy import dendrogram, linkage
+from sklearn.metrics import silhouette_score
+from sklearn.metrics import calinski_harabasz_score
+from sklearn.decomposition import PCA""",
+    10: """
+X = df[['speed', 'elevation', 'step_frequency','temp']]
+from sklearn.preprocessing import StandardScaler
+scaler = StandardScaler()
+X_scaled=scaler.fit_transform(X)""",
+    11: """import plotly.express as px
+plt = px.scatter_3d(X, x='speed', y='elevation', z='step_frequency',
+                 title='K-Means')""",
+    12: """from sklearn.cluster import KMeans
+wcss=[]
+for k in range(1,11):
+    Kmeans = KMeans(n_clusters=k,random_state=42)
+    Kmeans.fit(X_scaled)
+    wcss.append(Kmeans.inertia_)
+""",
+    13: """sns.lineplot(x=range(1,11), y=wcss, marker='o')""",
+    14: """cluster = KMeans(n_clusters=3)
+kmeans = cluster.fit_predict(X_scaled)""",
+    15: """
+plt.figure(figsize=(20, 15), dpi=100)
+scatter=plt.scatter(X_scaled[:,0],X_scaled[:,1],c=kmeans)
+plt.legend(*scatter.legend_elements(), title="Кластеры")""",
+    16: """from sklearn.cluster import DBSCAN
+DbscanCluster = DBSCAN(eps=0.5, min_samples=20)
+dbscan = DbscanCluster.fit_predict(X_scaled)""",
+    17: """from sklearn.mixture import GaussianMixture
+gmm = GaussianMixture(n_components=2, random_state=0)
+gmm_pred = gmm.fit_predict(X_scaled)""",
+    18: """harabKmeans = metrics.calinski_harabasz_score(X_scaled, kmeans)
+metrics.calinski_harabasz_score(X_scaled, kmeans)""",
+    19: """silhKmeans = metrics.silhouette_score(X_scaled, kmeans)
+metrics.silhouette_score(X_scaled, kmeans)""",
+    20: """metrics = ['Kmeans', 'dbscan','gmm_pred']
+scores = [harabKmeans, harabDBscan,harabgmm_pred]
+plt.bar(metrics, scores, color=['blue', 'green'])
+for i, v in enumerate(scores):
+    plt.text(i, v, f'{v:.2f}', ha='center', va='bottom')""",
+    21: """GEOPOINT(FLOAT([Широта]), FLOAT([Долгота]))
+MARKUP(
+    "ID точки: ", [ID точки], BR(),
+    "Трек: ", [ID трека], BR(),
+    "Время: ", [Дататайм], BR(),
+    "Скорость: ", [Скорость], " км/ч", BR(),
+    "Температура: ", [Температура ], "°C"
+)""",
 }
 
 def s(id: int = 1) -> bool:

{sklip-0.4.0.dist-info → sklip-0.5.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sklip
-Version: 0.4.0
+Version: 0.5.0
 Author-email: Your Name <your@email.com>
 Project-URL: Homepage, https://github.com/yourusername/skclip
 Classifier: Programming Language :: Python :: 3

sklip-0.5.0.dist-info/RECORD

@@ -0,0 +1,6 @@
+sklip/__init__.py,sha256=4lWCB5E2PJUnWvnPFRNEC5cgnZCr8bqqkx1Gu8bGPb0,122
+sklip/core.py,sha256=ucuAt056w_G3AcoS4_LOO2OKF1HNHA-TB3ZsykTn52k,5858
+sklip-0.5.0.dist-info/METADATA,sha256=mxJriWi4c_mFaGBWKtOtLYiMtXt1hXRtG8yte57zy7A,404
+sklip-0.5.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+sklip-0.5.0.dist-info/top_level.txt,sha256=V2T-257V83osKN3UDVUjuq-qK9nVZLF611GZPke9kiA,6
+sklip-0.5.0.dist-info/RECORD,,

sklip-0.4.0.dist-info/RECORD

@@ -1,6 +0,0 @@
-sklip/__init__.py,sha256=iJNC783kwR1HirR1pNR2MkETLNp9k6jlcjfT19ZbmJI,122
-sklip/core.py,sha256=kZ2wXJUCWoxU_Aje-oU6Ll60Z7TMSOZ4B8Q99_R5q5M,1502
-sklip-0.4.0.dist-info/METADATA,sha256=j0j6TFCvW1ZdAUsUWGUGVytCdEucK66EsqeW7l6__YU,404
-sklip-0.4.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
-sklip-0.4.0.dist-info/top_level.txt,sha256=V2T-257V83osKN3UDVUjuq-qK9nVZLF611GZPke9kiA,6
-sklip-0.4.0.dist-info/RECORD,,