seaborn 包应包含示例教程中引用的示例数据集或检索数据集的方法。
# Load the example planets dataset
planets = sns.load_dataset("planets")
当我在example folder 中查找“行星”数据集时,我看不到这些数据集。对函数“load_datasets”的一点探索表明,示例数据集来自seaborn-data file online,并且需要 pandas 包依赖项。
def load_dataset(name, cache=True, data_home=None, **kws):
"""Load a dataset from the online repository (requires internet).
Parameters
----------
name : str
Name of the dataset (`name`.csv on
https://github.com/mwaskom/seaborn-data). You can obtain list of
available datasets using :func:`get_dataset_names`
cache : boolean, optional
If True, then cache data locally and use the cache on subsequent calls
data_home : string, optional
The directory in which to cache data. By default, uses ~/seaborn_data/
kws : dict, optional
Passed to pandas.read_csv
"""
path = "https://github.com/mwaskom/seaborn-data/raw/master/{0}.csv"
full_path = path.format(name)
if cache:
cache_path = os.path.join(get_data_home(data_home),
os.path.basename(full_path))
if not os.path.exists(cache_path):
urlretrieve(full_path, cache_path)
full_path = cache_path
df = pd.read_csv(full_path, **kws)
if df.iloc[-1].isnull().all():
df = df.iloc[:-1]
if not pandas_has_categoricals:
return df
# Set some columns as a categorical type with ordered levels
if name == "tips":
df["day"] = pd.Categorical(df["day"], ["Thur", "Fri", "Sat", "Sun"])
df["sex"] = pd.Categorical(df["sex"], ["Male", "Female"])
df["time"] = pd.Categorical(df["time"], ["Lunch", "Dinner"])
df["smoker"] = pd.Categorical(df["smoker"], ["Yes", "No"])
if name == "flights":
df["month"] = pd.Categorical(df["month"], df.month.unique())
if name == "exercise":
df["time"] = pd.Categorical(df["time"], ["1 min", "15 min", "30 min"])
df["kind"] = pd.Categorical(df["kind"], ["rest", "walking", "running"])
df["diet"] = pd.Categorical(df["diet"], ["no fat", "low fat"])
if name == "titanic":
df["class"] = pd.Categorical(df["class"], ["First", "Second", "Third"])
df["deck"] = pd.Categorical(df["deck"], list("ABCDEFG"))
return df