我们从Python开源项目中，提取了以下8个代码示例，用于说明如何使用seaborn.violinplot()。
def overlap_visualize(): train,test,dev = load("nlpcc",filter=True) test = test.reindex(np.random.permutation(test.index)) df = test df['qlen'] = df['question'].str.len() df['alen'] = df['answer'].str.len() df['q_n_words'] = df['question'].apply(lambda row:len(row.split(' '))) df['a_n_words'] = df['answer'].apply(lambda row:len(row.split(' '))) def normalized_word_share(row): w1 = set(map(lambda word: word.lower().strip(), row['question'].split(" "))) w2 = set(map(lambda word: word.lower().strip(), row['answer'].split(" "))) return 1.0 * len(w1 & w2)/(len(w1) + len(w2)) df['word_share'] = df.apply(normalized_word_share, axis=1) plt.figure(figsize=(12, 8)) plt.subplot(1,2,1) sns.violinplot(x = 'flag', y = 'word_share', data = df[0:50000]) plt.subplot(1,2,2) sns.distplot(df[df['flag'] == 1.0]['word_share'][0:10000], color = 'green') sns.distplot(df[df['flag'] == 0.0]['word_share'][0:10000], color = 'red') print evaluation.evaluationBypandas(test,df['word_share']) plt.show('hold')
def plot_group(data_frame, path_output): # optional import import seaborn as sns path_output_image = os.path.join(path_output, "summary_statistics.png") # # Plotting swarmplot # plt.figure(num=None, figsize=(15, 7), dpi=120) # sns.set_style("whitegrid") # # plt.title('Violin plot with single measurements') # sns.violinplot(x="Group", y="DAB+ area", data=data_frame, inner=None) # sns.swarmplot(x="Group", y="DAB+ area", data=data_frame, color="w", alpha=.5) # plt.savefig(path_output_image) # # plt.tight_layout() sns.set_style("whitegrid") sns.set_context("talk") plt.figure(num=None, figsize=(15, 7), dpi=120) plt.ylim(0, 100) plt.title('Box plot') sns.boxplot(x="Group", y="DAB+ area, %", data=data_frame) plt.tight_layout() plt.savefig(path_output_image, dpi=300)
def plot_fnc(self, *args, **kwargs): sns.violinplot(*args, **kwargs)
def horizontal_violin_plot(data, ordered_genomes, title, xlabel, pdf, hue=None, x=None, y=None, xlim=None): """not so generic function that specifically produces a paired boxplot/violinplot""" fig, ax = plt.subplots() sns.violinplot(data=data, x=x, y=y, hue=hue, order=ordered_genomes, palette=choose_palette(ordered_genomes), saturation=boxplot_saturation, orient='h', cut=0, scale='count', ax=ax) fig.suptitle(title) ax.set_xlabel(xlabel) if xlim is not None: ax.set_xlim(xlim) multipage_close(pdf, tight_layout=False)
def sentence_length_vs_ponder_time(config,processed_data): plotting_data = [] for data in processed_data: steps = len(data["act_probs"]) hyp_length = sum([1 for x in data["hypothesis"] if x!="PAD"]) prem_length = sum([1 for x in data["premise"] if x!="PAD"]) avg_length = (hyp_length + prem_length)/2 correct = data["correct"] type_class = data["class"] plotting_data.append([steps, avg_length, correct, type_class]) plotting_data = pd.DataFrame(np.vstack(plotting_data), columns=["steps", "avg_length", "correct", "class"]) seaborn.violinplot(x="steps", y="avg_length", hue="correct",split=True, data=plotting_data, inner="quartile", scale="count") plt.show() # for class_type in [0.0,1.0,2.0]: # fig = plt.figure() # x_vals = [x[0] for x in plotting_data if (x[3]==class_type and x[2]==1.0)] # y_vals = [x[1] for x in plotting_data if (x[3]==class_type and x[2]==1.0)] # print("Class: ",class_type, "No. Correct: ", len(x_vals)) # plt.scatter(x_vals, y_vals,color="g") # # x_vals = [x[0] for x in plotting_data if (x[3]==class_type and x[2]==0.0)] # y_vals = [x[1] for x in plotting_data if (x[3]==class_type and x[2]==0.0)] # print("Class: ",class_type, "No. Incorrect: ", len(x_vals)) # # plt.scatter(x_vals, y_vals,color="r") # # ax = plt.gca() # ax.set_xlabel("ACT Steps") # ax.set_ylabel("avg hyp/premise length") # ax.set_title("test_title") # plt.show()
def violin_plot(filtered_data, output_file): plt.figure() plot = sns.violinplot( x="property_type", y="price_max", data=filtered_data, inner=None, figsize=(20, 20) ) plot.get_figure().savefig(output_file)
def figure2_1(): global figureIndex plt.figure(figureIndex) figureIndex += 1 sns.violinplot(data=np.random.randn(200,10) + np.random.randn(10)) plt.xlabel("Action") plt.ylabel("Reward distribution")
def gRNA_swarmplot(s1, s2, prefix=""): # Rank of gRNA change fig, axis = plt.subplots(3, 2, sharex=True, sharey=True, figsize=(8, 8)) axis = axis.flatten() for i, screen in enumerate(s2.columns[::-1]): s = s1.join(s2) # .fillna(0) s = s.iloc[np.random.permutation(len(s))] if ("TCR" in screen) or ("Jurkat" in screen) or ("stimulated" in screen) or ("unstimulated" in screen): s = s.ix[s.index[~s.index.str.contains("Wnt")]] if prefix.startswith("mid_screen-"): b = s["gDNA_Jurkat"] else: b = s["plasmid_pool_TCR"] x = s.ix[s.index[s.index.str.contains("Tcr")]] y = s.ix[s.index[s.index.str.contains("Essential")]] z = s.ix[s.index[s.index.str.contains("CTRL")]] b_x = b.ix[s.index[s.index.str.contains("Tcr")]] b_y = b.ix[s.index[s.index.str.contains("Essential")]] b_z = b.ix[s.index[s.index.str.contains("CTRL")]] elif ("WNT" in screen) or ("HEK" in screen): s = s.ix[s.index[~s.index.str.contains("Tcr")]] if prefix.startswith("mid_screen-"): if "_4_" in prefix: b = s["gDNA_HEKclone4"] else: b = s["gDNA_HEKclone6"] else: b = s["plasmid_pool_WNT"] x = s.ix[s.index[s.index.str.contains("Wnt")]] y = s.ix[s.index[s.index.str.contains("Essential")]] z = s.ix[s.index[s.index.str.contains("CTRL")]] b_x = b.ix[s.index[s.index.str.contains("Wnt")]] b_y = b.ix[s.index[s.index.str.contains("Essential")]] b_z = b.ix[s.index[s.index.str.contains("CTRL")]] fc_x = np.log2(1 + x[screen]) - np.log2(1 + b_x) fc_y = np.log2(1 + y[screen]) - np.log2(1 + b_y) fc_z = np.log2(1 + z[screen]) - np.log2(1 + b_z) fc_x.name = screen fc_y.name = "Essential" fc_z.name = "CTRL" sns.violinplot(x="variable", y="value", alpha=0.1, inner="box", data=pd.melt(pd.DataFrame([fc_x, fc_y, fc_z]).T), ax=axis[i]) sns.swarmplot(x="variable", y="value", alpha=0.5, data=pd.melt(pd.DataFrame([fc_x, fc_y, fc_z]).T), ax=axis[i]) axis[i].axhline(y=0, color='black', linestyle='--', lw=0.5) axis[i].set_title(screen) sns.despine(fig) fig.savefig(os.path.join(results_dir, "gRNA_counts.norm.{}.violin_swarmplot.svg".format(prefix)), bbox_inches="tight")
