def _update_plot(self, axis, view):
if self.plot_type == 'regplot':
sns.regplot(x=view.x,
y=view.y,
data=view.data,
ax=axis,
**self.style)
elif self.plot_type == 'boxplot':
self.style.pop('return_type', None)
self.style.pop('figsize', None)
sns.boxplot(view.data[view.y],
view.data[view.x],
ax=axis,
**self.style)
elif self.plot_type == 'violinplot':
sns.violinplot(view.data[view.y],
view.data[view.x],
ax=axis,
**self.style)
elif self.plot_type == 'interact':
sns.interactplot(view.x,
view.x2,
view.y,
data=view.data,
ax=axis,
**self.style)
elif self.plot_type == 'corrplot':
sns.corrplot(view.data, ax=axis, **self.style)
elif self.plot_type == 'lmplot':
sns.lmplot(x=view.x,
y=view.y,
data=view.data,
ax=axis,
**self.style)
elif self.plot_type in ['pairplot', 'pairgrid', 'facetgrid']:
map_opts = [(k, self.style.pop(k)) for k in self.style.keys()
if 'map' in k]
if self.plot_type == 'pairplot':
g = sns.pairplot(view.data, **self.style)
elif self.plot_type == 'pairgrid':
g = sns.PairGrid(view.data, **self.style)
elif self.plot_type == 'facetgrid':
g = sns.FacetGrid(view.data, **self.style)
for opt, args in map_opts:
plot_fn = getattr(sns, args[0]) if hasattr(
sns, args[0]) else getattr(plt, args[0])
getattr(g, opt)(plot_fn, *args[1:])
plt.close(self.handles['fig'])
self.handles['fig'] = plt.gcf()
else:
super(SNSFramePlot, self)._update_plot(axis, view)
def _update_plot(self, axis, view):
style = self._process_style(self.style[self.cyclic_index])
if self.plot_type == 'factorplot':
opts = dict(style, **({'hue': view.x2} if view.x2 else {}))
sns.factorplot(x=view.x, y=view.y, data=view.data, **opts)
elif self.plot_type == 'regplot':
sns.regplot(x=view.x, y=view.y, data=view.data, ax=axis, **style)
elif self.plot_type == 'boxplot':
style.pop('return_type', None)
style.pop('figsize', None)
sns.boxplot(view.data[view.y], view.data[view.x], ax=axis, **style)
elif self.plot_type == 'violinplot':
if view.x:
sns.violinplot(view.data[view.y],
view.data[view.x],
ax=axis,
**style)
else:
sns.violinplot(view.data, ax=axis, **style)
elif self.plot_type == 'interact':
sns.interactplot(view.x,
view.x2,
view.y,
data=view.data,
ax=axis,
**style)
elif self.plot_type == 'corrplot':
sns.corrplot(view.data, ax=axis, **style)
elif self.plot_type == 'lmplot':
sns.lmplot(x=view.x, y=view.y, data=view.data, ax=axis, **style)
elif self.plot_type in ['pairplot', 'pairgrid', 'facetgrid']:
style_keys = list(style.keys())
map_opts = [(k, style.pop(k)) for k in style_keys if 'map' in k]
if self.plot_type == 'pairplot':
g = sns.pairplot(view.data, **style)
elif self.plot_type == 'pairgrid':
g = sns.PairGrid(view.data, **style)
elif self.plot_type == 'facetgrid':
g = sns.FacetGrid(view.data, **style)
for opt, args in map_opts:
plot_fn = getattr(sns, args[0]) if hasattr(
sns, args[0]) else getattr(plt, args[0])
getattr(g, opt)(plot_fn, *args[1:])
plt.close(self.handles['fig'])
self.handles['fig'] = plt.gcf()
else:
super(SNSFramePlot, self)._update_plot(axis, view)
def _update_plot(self, axis, view):
style = self._process_style(self.style[self.cyclic_index])
if self.plot_type == 'factorplot':
opts = dict(style, **({'hue': view.x2} if view.x2 else {}))
sns.factorplot(x=view.x, y=view.y, data=view.data, **opts)
elif self.plot_type == 'regplot':
sns.regplot(x=view.x, y=view.y, data=view.data,
ax=axis, **style)
elif self.plot_type == 'boxplot':
style.pop('return_type', None)
style.pop('figsize', None)
sns.boxplot(view.data[view.y], view.data[view.x], ax=axis,
**style)
elif self.plot_type == 'violinplot':
if view.x:
sns.violinplot(view.data[view.y], view.data[view.x], ax=axis,
**style)
else:
sns.violinplot(view.data, ax=axis, **style)
elif self.plot_type == 'interact':
sns.interactplot(view.x, view.x2, view.y,
data=view.data, ax=axis, **style)
elif self.plot_type == 'corrplot':
sns.corrplot(view.data, ax=axis, **style)
elif self.plot_type == 'lmplot':
sns.lmplot(x=view.x, y=view.y, data=view.data,
ax=axis, **style)
elif self.plot_type in ['pairplot', 'pairgrid', 'facetgrid']:
style_keys = list(style.keys())
map_opts = [(k, style.pop(k)) for k in style_keys if 'map' in k]
if self.plot_type == 'pairplot':
g = sns.pairplot(view.data, **style)
elif self.plot_type == 'pairgrid':
g = sns.PairGrid(view.data, **style)
elif self.plot_type == 'facetgrid':
g = sns.FacetGrid(view.data, **style)
for opt, args in map_opts:
plot_fn = getattr(sns, args[0]) if hasattr(sns, args[0]) else getattr(plt, args[0])
getattr(g, opt)(plot_fn, *args[1:])
if self._close_figures:
plt.close(self.handles['fig'])
self.handles['fig'] = plt.gcf()
else:
super(SNSFramePlot, self)._update_plot(axis, view)
def sea():
source_data = pd.read_csv(
'/Users/saracamnasio/Dropbox/Research/Projects/UnusuallyRB/2016_Analysis/input/CP_results.csv'
)
sns.pairplot(source_data,
hue="Classification",
vars=["Opt_SpT", "Lmin_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["Opt_SpT", "Lmax_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["JK_Dev", "Lmin_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["HK_Dev", "Lmin_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["JH_Dev", "Lmin_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["JK_Dev", "Lmax_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["HK_Dev", "Lmax_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
sns.pairplot(source_data,
hue="Classification",
vars=["JH_Dev", "Lmax_mu"],
palette="Set2",
diag_kind="kde",
size=2.5)
import matplotlib.pyplot as plt
import pandas as pd
import seaborn.apionly as sns
flowers = pd.read_csv('data/iris.csv')
g = sns.pairplot(data=flowers,
y_vars=['petal_length', 'petal_width'],
x_vars=['sepal_length', 'sepal_width'],
hue='species',
plot_kws={'linewidth': 0})
legend = g.fig.legends[0]
legend.draggable(True)
plt.show(block=True)
g.fig.savefig('iris-pairs.png', dpi=300)
get_ipython().magic('pinfo sns.pairplot')
get_ipython().magic('ls ')
color_palette = np.array([[71, 117, 167],
[120, 121, 122],
[248, 213, 95],
[140, 175, 83],
[152, 109, 163],
[169, 93, 100]]) / 255
cars = pd.read_csv('cars.csv')
cars = pd.read_csv('data/cars.csv')
origin_dict = {1: 'USA', 2: 'Europe', 3: 'Japan'}
cars['origin name'] = cars['origin'].apply(origin_dict.get)
sns.pairplot(data=cars,
x_vars=['weight'],
y_vars=['mpg'],
hue='origin name',
palette=dict(zip(origin_dict.values(), color_palette)))
len(set(cars['name']))
cars.shape
sns.pairplot(data=cars,
x_vars=['weight'],
y_vars=['mpg'],
hue='origin name')
_.fig.legends[0].draggable(True)
_.fig.legends[0].draggable(False)
_16.fig.legends[0].draggable(False)
_16.fig.savefig('cars-scatter.png', dpi=300)
boston_data = load_boston()
train_data = np.array(boston_data.data)
train_labels = np.array(boston_data.target)
num_features = boston_data.data.shape[1]
unique_labels = np.unique(train_labels)
num_classes = len(unique_labels)
print("The boston dataset has " + str(num_features) + " features")
print(boston_data.feature_names)
# Put everything into a Pandas DataFrame
data = pd.DataFrame(data=np.c_[train_data], columns=boston_data.feature_names)
# print(tabulate(data, headers='keys', tablefmt='psql'))
# Compute the covariance matrix
cov_mat_boston = np.cov(train_data.T)
print("Covariance matrix")
print(cov_mat_boston)
# Normalize the data and then recompute the covariance matrix
normalized_train_data = helpers.normalize_data(train_data)
normalized_cov_mat_boston = np.cov(normalized_train_data.T)
print("Normalized data covariance matrix")
print(normalized_cov_mat_boston)
# create scatterplot matrix
fig = sns.pairplot(data=data, hue='CRIM')
plt.show()
'CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX',
'PTRATIO', 'B', 'LSTAT', 'MEDV'
]
df.shape
# ## Visualizzazione delle caratteristiche del dataset
# Matrice delle distribuzioni mutue delle feature. Sulla diagonale, distribuzione delle singole feature
# +
cols = ['LSTAT', 'RM', 'INDUS', 'AGE', 'MEDV']
fig = plt.figure(figsize=(16, 8))
sns.pairplot(df[cols],
height=4,
diag_kind='kde',
plot_kws=dict(color=colors[8]),
diag_kws=dict(shade=True, alpha=.7, color=colors[0]))
plt.show()
# -
# Visualizzazione della matrice di correlazione. Alla posizione $(i,j)$ il coefficiente di correlazione (lineare) tra le feature $i$ e $j$. Valore in $[-1,1]$: $1$ correlazione perfetta, $-1$ correlazione inversa perfetta, $0$ assenza di correlazione
cm = np.corrcoef(df[cols].values.T)
plt.figure(figsize=(12, 4))
hm = sns.heatmap(cm,
cbar=True,
annot=True,
square=True,
fmt='.2f',
annot_kws={'size': 10},
# Testing results agains existing function
print("My covariance function: {}".format(covariance([1, 3, 4], [1, 0, 2])))
print("Numpy covariance function: {}".format(np.cov([1, 3, 4], [1, 0, 2])))
def correlation(X, Y):
return (covariance(X, Y) / (np.std(X, ddof=1) * np.std(Y, ddof=1))
) # we had to indicat ddof=1 the unbiased std
print("My Correlation: {}".format(correlation([1, 1, 4, 3], [1, 0, 2, 2])))
print("Numpy corrcoef: {}".format(np.corrcoef([1, 1, 4, 3], [1, 0, 2, 2])))
# Start seeing a general view of the data to try to determine what is the best approach
sns.pairplot(iris2, height=3.0)
plt.show()
# Based on the results, we chose
X = iris2['petal_width']
Y = iris2['petal_length']
plt.scatter(X, Y)
# plt.show()
# Creating the prediction function
def predict(alpha, beta, x_i):
return beta * x_i + alpha
# ------------------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------------------
# Create scatterplot
scatter_feature_name_1 = 'color_intensity'
scatter_feature_name_2 = 'alcohol'
fig = plt.scatter(data[scatter_feature_name_1], data[scatter_feature_name_2])
plt.xlabel(scatter_feature_name_1)
plt.ylabel(scatter_feature_name_2)
plt.show()
# Create scatterplot matrix
fig = sns.pairplot(data=data[[
'alcohol', 'color_intensity', 'malic_acid', 'magnesium', 'category'
]],
hue='category')
plt.show()
# ------------------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------------------
# Create bee swarm plot
sns.swarmplot(x='category', y='total_phenols', data=data)
plt.show()
# ------------------------------------------------------------------------------------------------
# ------------------------------------------------------------------------------------------------
Created on Mon Jan 29 10:40:44 2018
@author: aditya royal
"""
import pandas as pd
import seaborn.apionly as sns
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
obj = pd.read_csv('C:/Users/aditya royal/Downloads/MPG.csv')
mpg_year = obj.groupby(['model year'])['mpg'].mean()
mpg_year.plot()
plt.scatter(x=obj['mpg'], y=obj['horsepower'])
plt.show()
plt.bar(obj['mpg'], obj['origin'])
#plt.bar(obj['car manufacturer'],obj['origin'])
origin_group = obj.groupby(['cylinders'])
plt.hist(obj['mpg'])
for name, group in origin_group:
plt.boxplot(origin_group['mpg'].get_group(name).values)
plt.show()
#sns.heatmap(obj[['mpg','cylinders']].T)
plt.scatter(x=obj['weight'],
y=obj['mpg'],
c=list(obj['origin'].values),
cmap=matplotlib.colors.ListedColormap(['red', 'green', 'blue']))
sns.pairplot(
obj[['mpg', 'displacement', 'horsepower', 'weight',
'acceleration']].dropna())
# In[53]: # This makes a new datafram which removes the column that tells whether it is malignant or benign. y = data.type data_p=data.drop(columns="type") #create a new data array data_p.head() # In[57]: data_pair = data_mean.drop(columns=["ID"]) sns.pairplot(data_pair,hue='type') # # First Machine Learning Model # # This uses the linear model method with logistic regression to perform machine learning. This model is fitted to the mean features and tumor types. # In[17]: from sklearn import linear_model from sklearn import model_selection xreg = data_mean[['mean radius','mean texture','mean perimeter','mean area','mean smoothness','mean compactness','mean concavity','mean concave points','mean symmetry','mean fractal dimension']] # this makes an x variable with all the mean features yreg = data.type # this makes the y variable the type of tumor column clf = linear_model.LogisticRegression() # this sets up logistic regression clf.fit(xreg, yreg) # this fits it to the new x variable and y variable
