Consulting - Quality
Difference makes the DIFFERENCE
SEABORN HISTOGRAM
Padhai - Classwork
Distribution of Data - Seaborn Package¶
In [15]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
sns.set(color_codes = True)
In [8]:
x = np.random.normal(size=1000)
In [16]:
sns.distplot(x)
Out[16]:
In [17]:
sns.distplot(x, kde = False)
Out[17]:
In [13]:
sns.set(color_codes = True)
In [18]:
sns.distplot(x, kde = False, rug = True)
Out[18]:
In [19]:
sns.distplot(x, bins=50, kde=False, rug=True)
Out[19]:
In [20]:
sns.kdeplot(x)
Out[20]:
In [21]:
sns.kdeplot(x, shade=True)
Out[21]:
In [22]:
y = np.random.uniform(size=1000)
In [25]:
sns.kdeplot(y, shade=True)
sns.kdeplot(x, shade=True);
with real datasets from seaborn package¶
In [26]:
d = sns.load_dataset('diamonds')
In [27]:
d
Out[27]:
In [28]:
d.info()
In [30]:
sns.distplot(d.carat)
# the outcome is not uni-modal distribution
Out[30]:
In [32]:
sns.distplot(d.price)
# the outcome is a long tailed distribution - right skewed distribution
Out[32]:
In [33]:
sns.distplot(d.x)
Out[33]:
In [34]:
sns.distplot(d.x, rug=True)
Out[34]:
In [35]:
sns.distplot(d.sample(1000).x, rug = True)
Out[35]:
In [36]:
sns.kdeplot(d.x)
sns.kdeplot(d.y)
sns.kdeplot(d.z)
Out[36]:
In [37]:
sns.kdeplot(d.x, shade=True)
sns.kdeplot(d.y, shade=True)
sns.kdeplot(d.z, shade=True)
Out[37]:
In [39]:
sns.kdeplot(d.x, shade=True)
sns.kdeplot(d.y, shade=True)
# x and y dataset is almost similar in nature
Out[39]:
In [ ]: