Python Data Science Essentials

import numpy as np import pandas as pd import matplotlib.pyplot as plt import matplotlib as mpl

x = np.linspace(0, 5, 50) y_cos = np.cos(x) y_sin = np.sin(x)

plt.plot(x,y_cos, 'r--') # plot series of coordinates as a line plt.plot(x,y_sin, 'b-') plt.xlabel('x') # adds label to x axis plt.ylabel('y') # adds label to y axis plt.title('title') # adds a title plt.show() # close a figure

from sklearn.datasets import make_blobs D = make_blobs(n_samples=100, n_features=2, centers=3, random_state=7) groups = D[1] coordinates = D[0]

plt.plot(coordinates[groups==0,0], coordinates[groups==0,1], 'ys', label='group 0') # yellow square plt.plot(coordinates[groups==1,0], coordinates[groups==1,1], 'm*', label='group 1') # magenta stars plt.plot(coordinates[groups==2,0], coordinates[groups==2,1], 'rD', label='group 2') # red diamonds plt.ylim(-2,10) # redefines the limits of y axis plt.yticks([10,6,2,-2]) # redefines y axis ticks plt.xticks([-15,-5,5,15]) # redefines x axis ticks plt.grid() # adds a grid plt.annotate('Squares', (-12,2.5)) # prints text at coordinates plt.annotate('Stars', (0,6)) plt.annotate('Diamonds', (10,3)) plt.legend(loc='lower left', numpoints= 2) # places a legend of labelled items plt.gcf().set_size_inches(8, 6) plt.show()

x = np.random.normal(loc=0.0, scale=1.0, size=500) z = np.random.normal(loc=3.0, scale=1.0, size=500) plt.hist(np.column_stack((x,z)), bins=20, histtype='step', #'bar' color = ['c','b'], stacked=False) plt.grid() plt.show()

from sklearn.datasets import load_iris iris = load_iris() average = np.mean(iris.data, axis=0) std = np.std(iris.data, axis=0) range_ = range(np.shape(iris.data)[1])

plt.subplot(1,2,1) # defines 1 row, 2 columns panel, activates figure 1 plt.title('Horizontal bars') plt.barh(range_,average, color="r", xerr=std, alpha=0.4, align="center") plt.yticks(range_, iris.feature_names) plt.subplot(1,2,2) # defines 1 row 2 column panel, activates figure 2 plt.title('Vertical bars') plt.bar(range_,average, color="b", yerr=std, alpha=0.4, align="center") plt.xticks(range_, range_) plt.show()

# from sklearn.datasets import fetch_olivetti_faces dataset = fetch_olivetti_faces(shuffle=True, random_state=5) photo = 1 for k in range(6): plt.subplot(2, 3, k+1) plt.imshow(dataset.data[k].reshape(64, 64), cmap=plt.cm.gray, interpolation='nearest') plt.title('subject '+str(dataset.target[k])) plt.axis('off') plt.show()

from sklearn.datasets import load_digits digits = load_digits() for number in range(1,10): fig = plt.subplot(3, 3, number) fig.imshow(digits.images[number], cmap='binary', interpolation='none', extent=[0,8,0,8]) fig.set_xticks(np.arange(0, 9)) fig.set_yticks(np.arange(0, 9)) # fig.set_xticks(np.arange(0, 21)) # fig.set_yticks(np.arange(0, 21)) fig.grid() plt.show()

plt.imshow(digits.images[0], cmap='binary', interpolation='none', extent=[0,8,0,8]) # Extent defines the images max and min # of the horizontal and vertical values plt.grid()

iris_df = pd.DataFrame(iris.data, columns=iris.feature_names) groups = list(iris.target) iris_df['groups'] = pd.Series([iris.target_names[k] for k in groups])

boxplots = iris_df.boxplot(return_type='axes')

boxplots = iris_df.boxplot(column='sepal length (cm)', by='groups', return_type='axes')

densityplot = iris_df.plot(kind='density')

single_distribution = iris_df['petal width (cm)'].plot(kind='hist', alpha=0.5)

iris_df.columns

iris_df['groups'].value_counts()

colors_palette = {0: 'red', 1: 'yellow', 2:'blue'} # groups represents the y label colors = [colors_palette[c] for c in groups] simple_scatterplot = iris_df.plot(kind='scatter', x=0, y=1, c=colors)

hexbin = iris_df.plot(kind='hexbin', x=0, y=1, gridsize=10)

from pandas.plotting import scatter_matrix colors_palette = {0: "red", 1: "green", 2: "blue"} colors = [colors_palette[c] for c in groups] matrix_of_scatterplots = scatter_matrix(iris_df, alpha=0.2, figsize=(6, 6), color=colors, diagonal='kde')

from pandas.plotting import parallel_coordinates pll = parallel_coordinates(iris_df,'groups')