def make_plot(X_train, y_train, X, y, test_data, model, model_name, features, response):
feature = X.columns
f, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, sharey=False)
sns.regplot(X[feature[4]], y, test_data, ax=ax1)
sns.boxplot(X[feature[4]], y, color="Blues_r", ax=ax2)
model.fit(X_train, y_train)
sns.residplot(X[feature[4]], (model.predict(X) - y) ** 2, color="indianred", lowess=True, ax=ax3)
if model_name is 'linear':
sns.interactplot(X[feature[3]], X[feature[4]], y, ax=ax4, filled=True, scatter_kws={"color": "dimgray"}, contour_kws={"alpha": .5})
elif model_name is 'logistic':
pal = sns.blend_palette(["#4169E1", "#DFAAEF", "#E16941"], as_cmap=True)
levels = np.linspace(0, 1, 11)
sns.interactplot(X[feature[3]], X[feature[4]], y, levels=levels, cmap=pal, logistic=True)
else:
pass
ax1.set_title('Regression')
ax2.set_title(feature[4]+' Value')
ax3.set_title(feature[4]+' Residuals')
ax4.set_title('Two-value Interaction')
f.tight_layout()
plt.savefig(model_name+'_'+feature[4], bbox_inches='tight')
# Multi-variable correlation significance level
f, ax = plt.subplots(figsize=(10, 10))
cmap = sns.blend_palette(["#00008B", "#6A5ACD", "#F0F8FF",
"#FFE6F8", "#C71585", "#8B0000"], as_cmap=True)
sns.corrplot(test_data, annot=False, diag_names=False, cmap=cmap)
ax.grid(False)
ax.set_title('Multi-variable correlation significance level')
plt.savefig(model_name+'_multi-variable_correlation', bbox_inches='tight')
# complete coefficient plot - believe this is only for linear regression
sns.coefplot("diagnosis ~ "+' + '.join(features), test_data, intercept=True)
plt.xticks(rotation='vertical')
plt.savefig(model_name+'_coefficient_effects', bbox_inches='tight')
def volcano_plot(tissue_array, type=None, out):
"""Generates a tissue specific volcano plot based on the log2 fold change (x) and log10(p-values from Tukeys T-test
Args:
tissue_array (array): Tissue specific array
type (str): Tissue data set was derived from; used for labeling plot
out (str): The title of the Volcano plot generated <Tissue>+'-<out>'.pdf'
Returns:
Nothing. Generates a Volcano plot for a tissue specific array
"""
plt.clf()
sns.set(font_scale=1.4)
from scipy.stats import ttest_ind
filt = tissue_array[np.all(tissue_array != 0, axis=1)]
x = log2(filt[:, -2:].mean(axis=1)) - log2(filt[:, :3].mean(axis=1))
y = -log10(ttest_ind(filt[:, -2:], filt[:, :2], axis=1)[1:][0])
xy = column_stack((x, y))
xy = xy[~isinf(xy).any(axis=1)]
sns.regplot(xy[:, 0], xy[:, 1], fit_reg=False, color='k',
scatter_kws={'alpha': 0.9, 's': 2.0, 'rasterized': False, 'zorder': 1}).set_ylim(0, )
de = xy[abs(xy[:, 0]) > 1, :]
de = de[de[:, 1] > 2, :]
up = sum(de[:, 0] > 0)
down = sum(de[:, 0] < 0)
sns.regplot(de[:, 0], de[:, 1], fit_reg=False, color='r',
scatter_kws={'alpha': 0.9, 's': 2.5, 'rasterized': False, 'zorder': 1})
plt.axhline(y=2.0, linewidth=.8, color='red', linestyle='dashed')
plt.axvline(x=1.0, linewidth=.8, color='red', linestyle='dashed')
plt.axvline(x=-1.0, linewidth=.8, color='red', linestyle='dashed')
plt.xlabel(r'$\log_2$(KO/WT)')
plt.ylabel(r'-$\log_{10}$ p-value')
plt.suptitle('%s: Downregulated genes: %s Upregulated genes: %s ' % (type, down, up))
plt.savefig('%s-'+out % (type), format='pdf')
def moran_plot(IM):
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pysal as ps
y_norm = normalize(IM.y)
y_lag = ps.lag_spatial(IM.w, IM.y)
y_lag_norm = normalize(y_lag)
dados = pd.DataFrame({'y':IM.y, 'y_norm':y_norm,
'y_lag':y_lag, 'y_lag_norm':y_lag_norm})
f, ax = plt.subplots(1, figsize=(7, 5))
sns.regplot('y_norm', 'y_lag_norm', data=dados, ci=None,
color='black', line_kws={'color':'red'})
plt.axvline(0, c='gray', alpha=0.7)
plt.axhline(0, c='gray', alpha=0.7)
limits = np.array([y_norm.min(), y_norm.max(), y_lag_norm.min(), y_lag_norm.max()])
limits = np.abs(limits).max()
border = 0.02
ax.set_xlim(- limits - border, limits + border)
ax.set_ylim(- limits - border, limits + border)
plt.show();
def aligned_residuals(pca):
"""
Plots error components along with bootstrap
resampled error surface. Provides another
statistical method to estimate the variance
of a dataset.
"""
A = pca.rotated()
fig, axes = P.subplots(2,1,
sharex=True, frameon=False)
fig.subplots_adjust(hspace=0, wspace=0.1)
kw = dict(c="#555555", s=40, alpha=0.5)
#lengths = attitude.pca.singular_values[::-1]
lengths = (A[:,i].max()-A[:,i].min() for i in range(3))
titles = (
"Long cross-section (axis 3 vs. axis 1)",
"Short cross-section (axis 3 vs. axis 2)")
for title,ax,(a,b) in zip(titles,axes,
[(0,2),(1,2)]):
seaborn.regplot(A[:,a], A[:,b], ax=ax)
ax.text(0,1,title,
verticalalignment='top',
transform=ax.transAxes)
ax.autoscale(tight=True)
for spine in ax.spines.itervalues():
spine.set_visible(False)
ax.set_xlabel("Meters")
return fig
def explore(wine_set):
low = wine_set[wine_set['quality'] <= 5]
medium = wine_set[(wine_set['quality'] == 6) | (wine_set['quality'] == 7)]
high = wine_set[wine_set['quality'] > 7]
print('association between wine`s density and residual sugar for wines \nof `low` quality')
print(scipy.stats.pearsonr(low['density'], low["residual_sugar"]))
print('\nof `medium` quality')
print(scipy.stats.pearsonr(medium['density'], medium["residual_sugar"]))
print('\nof `high` quality')
print(scipy.stats.pearsonr(high['density'], high["residual_sugar"]))
scat0 = seaborn.regplot(x="density", y="residual_sugar", fit_reg=True, data=low)
plt.xlabel("Density of wine")
plt.ylabel("Residual sugar in wine, gram")
plt.title("Association between wine's density and residual sugar for wines of `low` quality")
plt.show()
scat0 = seaborn.regplot(x="density", y="residual_sugar", fit_reg=True, data=medium)
plt.xlabel("Density of wine")
plt.ylabel("Residual sugar in wine, gram")
plt.title("Association between wine's density and residual sugar for wines of `medium` quality")
plt.show()
scat0 = seaborn.regplot(x="density", y="residual_sugar", fit_reg=True, data=high)
plt.xlabel("Density of wine")
plt.ylabel("Residual sugar in wine, gram")
plt.title("Association between wine's density and residual sugar for wines of `high` quality")
plt.show()
def plot_building_temp():
sns.set_context("paper", font_scale=1.5)
b = "AZ0000FF"
s = "KTUS"
filelist = glob.glob(os.getcwd() + "/csv_FY/testWeather/{0}*.csv".format(b))
dfs = [pd.read_csv(csv) for csv in filelist]
col = "eui_gas"
dfs2 = [df[[col, "month", "year"]] for df in dfs]
df3 = pd.concat(dfs2)
temp = pd.read_csv(os.getcwd() + "/csv_FY/weather/weatherData_meanTemp.csv")
temp["year"] = temp["Unnamed: 0"].map(lambda x: float(x[:4]))
temp["month"] = temp["Unnamed: 0"].map(lambda x: float(x[5:7]))
temp.set_index(pd.DatetimeIndex(temp["Unnamed: 0"]), inplace=True)
temp = temp[[s, "month", "year"]]
joint2 = pd.merge(df3, temp, on=["year", "month"], how="inner")
joint2.to_csv(os.getcwd() + "/csv_FY/testWeather/test_temp.csv", index=False)
sns.lmplot(s, col, data=joint2, col="year", fit_reg=False)
plt.xlim((joint2[s].min() - 10, joint2[s].max() + 10))
plt.ylim((0, joint2[col].max() + 0.1))
P.savefig(os.getcwd() + "/csv_FY/testWeather/plot/scatter_temp_byyear.png", dpi=150)
plt.close()
joint2 = joint2[(2012 < joint2["year"]) & (joint2["year"] < 2015)]
sns.regplot(s, col, data=joint2, fit_reg=False)
plt.xlim((joint2[s].min() - 10, joint2[s].max() + 10))
plt.ylim((0, joint2[col].max() + 0.1))
P.savefig(os.getcwd() + "/csv_FY/testWeather/plot/scatter_temp_1314.png", dpi=150)
plt.close()
def plot_energy_temp(df_energy, df_temp, theme, b, s):
df = pd.DataFrame({'energy': df_energy[theme], 'temp': df_temp[s]})
sns.regplot('temp', 'energy', data=df, fit_reg=False)
P.savefig(os.getcwd() + '/plot_FY_weather/{2}/{0}_{1}.png'.format(b, s, theme), dpi = 150)
plt.title('Temperature-{0} plot: {1}, {2}'.format(theme, b, s))
plt.close()
return
def plot_energy_temp(df_energy, df_temp, theme, b, s):
df = pd.DataFrame({"energy": df_energy[theme], "temp": df_temp[s]})
sns.regplot("temp", "energy", data=df, fit_reg=False)
P.savefig(os.getcwd() + "/plot_FY_weather/{2}/{0}_{1}.png".format(b, s, theme), dpi=150)
plt.title("Temperature-{0} plot: {1}, {2}".format(theme, b, s))
plt.close()
return
def seaborn_plot_rolling(df_name=df_default_name):
my_df = load_df(df_name)
import seaborn as sns
import matplotlib.pyplot as plt
sns.regplot(x="age", y="mean_mod_50", data=my_df)
plt.show()
def seaborn_plot(df_name=df_default_name):
my_df = load_df(df_name)
import seaborn as sns
import matplotlib.pyplot as plt
sns.regplot(x="age", y="mod_acquire", data=my_df)
plt.show()
def plot_offense_vs_defense_spacing(spacing_data):
"""
Plot of offensive vs. defensive spacing for games
Args:
spacing_data (pd.DataFrame): Dataframe with columns of spacing data
['home_offense_areas', 'home_defense_areas',
'away_offense_areas', 'away_defense_areas']
save_fig (bool): if True, save plot to temp/ directory
Returns None
Also, shows plot.
"""
sns.regplot(spacing_data.away_offense_areas,
spacing_data.home_defense_areas,
fit_reg=True, color=sns.color_palette()[0],
ci=None)
sns.regplot(spacing_data.home_offense_areas,
spacing_data.away_defense_areas,
fit_reg=False, color=sns.color_palette()[0],
ci=None)
plt.xlabel('Average Offensive Spacing (sq ft)', fontsize=16)
plt.ylabel('Average Defensive Spacing (sq ft)', fontsize=16)
plt.title('Offensive spacing robustly induces defensive spacing',
fontsize=16)
plt.savefig('temp/OffenseVsDefense.png')
plt.close()
return None
def report_model_results(input_data, fit_model, name, filename):
order = r_forecast.arimaorder(fit_model)
print name + " ({},{},{})".format(*order)
print
try:
intercept, intercept_se = r_stats.coef(fit_model).rx2("intercept")[0], numpy.sqrt(r_stats.vcov(fit_model).rx2("intercept", "intercept")[0])
print "Intercept:", intercept, "+-", intercept_se
except:
print "No intercept"
print
residuals = numpy.array(r_stats.residuals(fit_model)[sum(order):])
residuals_mask = ~numpy.isnan(residuals)
fit_model_err = numpy.nansum(residuals**2)
baseline_err = numpy.sum((numpy.nanmean(input_data) - input_data[sum(order):][residuals_mask])**2)
print name + " model squared error: ", fit_model_err, "({} NA residuals)".format(numpy.count_nonzero(numpy.isnan(residuals)))
print "No model squared error:" + " " * len(name), baseline_err
print "-> R^2:", 1 - fit_model_err / baseline_err
print
print
plt.figure()
plt.axis('equal')
seaborn.regplot(input_data[sum(order):], input_data[sum(order):] - residuals)
plt.savefig(filename)
plt.close()
def plot_returns_cmp(self, only_show_returns=False, only_info=False):
"""考虑资金情况下的度量，进行与benchmark的收益度量对比，收益趋势，资金变动可视化，以及其它度量信息，不涉及benchmark"""
self.log_func('买入后卖出的交易数量:{}'.format(self.order_has_ret.shape[0]))
self.log_func('胜率:{:.4f}%'.format(self.win_rate * 100))
self.log_func('平均获利期望:{:.4f}%'.format(self.gains_mean * 100))
self.log_func('平均亏损期望:{:.4f}%'.format(self.losses_mean * 100))
self.log_func('盈亏比:{:.4f}'.format(self.win_loss_profit_rate))
self.log_func('策略收益: {:.4f}%'.format(self.algorithm_period_returns * 100))
self.log_func('策略年化收益: {:.4f}%'.format(self.algorithm_annualized_returns * 100))
self.log_func('策略买入成交比例:{:.4f}%'.format(self.buy_deal_rate * 100))
self.log_func('策略资金利用率比例:{:.4f}%'.format(self.cash_utilization * 100))
self.log_func('策略共执行{}个交易日'.format(self.num_trading_days))
if only_info:
return
self.algorithm_cum_returns.plot()
plt.legend(['algorithm returns'], loc='best')
plt.show()
if only_show_returns:
return
sns.regplot(x=np.arange(0, len(self.algorithm_cum_returns)), y=self.algorithm_cum_returns.values)
plt.show()
sns.distplot(self.capital.capital_pd['capital_blance'], kde_kws={"lw": 3, "label": "capital blance kde"})
plt.show()
def versus(data, x, y, xlabel="ratio", ylabels=("growth1", "growth2"), outfn="versus"):
plt.figure(figsize=(12, 6))
re_data = reconfigure_data(data, x, y)
# series1 = data[(data[x] > 1)]
# series2 = data[(data[x] < 1)]
#
# growth1 = pd.concat([series1[y[0]], series2[y[1]]])
# growth2 = pd.concat([series1[y[1]], series2[y[0]]])
# ratio = pd.concat([series1[x], 1 / series2[x]])
#
# indata = {}
# indata[xlabel] = ratio
# indata[ylabels[0]] = growth1
# indata[ylabels[1]] = growth2
# re_data = pd.DataFrame(indata)
plt.subplot(131)
sns.regplot(x="x", y="y1", data=re_data)
shared.add_stats(re_data, "x", "y1")
sns.despine()
plt.subplot(132)
sns.regplot(x="x", y="y2", data=re_data)
shared.add_stats(re_data, "x", "y2")
sns.despine()
ax = plt.subplot(133)
swarm(ax, re_data, ylabels[0], ylabels[1], "growth rate (\si{\per\hour})")
plt.tight_layout()
plt.savefig("ParA_inheritance/{0}.pdf".format(outfn))
def plot_building_temp():
sns.set_context("paper", font_scale=1.5)
b = 'AZ0000FF'
s = 'KTUS'
filelist = glob.glob(os.getcwd() + '/csv_FY/testWeather/{0}*.csv'.format(b))
dfs = [pd.read_csv(csv) for csv in filelist]
col = 'eui_gas'
dfs2 = [df[[col, 'month', 'year']] for df in dfs]
df3 = (pd.concat(dfs2))
temp = pd.read_csv(os.getcwd() + '/csv_FY/weather/weatherData_meanTemp.csv')
temp['year'] = temp['Unnamed: 0'].map(lambda x: float(x[:4]))
temp['month'] = temp['Unnamed: 0'].map(lambda x: float(x[5:7]))
temp.set_index(pd.DatetimeIndex(temp['Unnamed: 0']), inplace=True)
temp = temp[[s, 'month', 'year']]
joint2 = pd.merge(df3, temp, on = ['year', 'month'], how = 'inner')
joint2.to_csv(os.getcwd() + '/csv_FY/testWeather/test_temp.csv', index=False)
sns.lmplot(s, col, data=joint2, col='year', fit_reg=False)
plt.xlim((joint2[s].min() - 10, joint2[s].max() + 10))
plt.ylim((0, joint2[col].max() + 0.1))
P.savefig(os.getcwd() + '/csv_FY/testWeather/plot/scatter_temp_byyear.png', dpi=150)
plt.close()
joint2 = joint2[(2012 < joint2['year']) & (joint2['year'] < 2015)]
sns.regplot(s, col, data=joint2, fit_reg=False)
plt.xlim((joint2[s].min() - 10, joint2[s].max() + 10))
plt.ylim((0, joint2[col].max() + 0.1))
P.savefig(os.getcwd() + '/csv_FY/testWeather/plot/scatter_temp_1314.png', dpi=150)
plt.close()
def show_friction_line(self, sns_context="talk"):
"""
Shows results from dF/dN friction test
:param sns_context:
:return: None
"""
self.mean_friction_frame()
p_dat = self.mean_fric_frame[self.mean_fric_frame['direction'] == 0]
n_dat = self.mean_fric_frame[self.mean_fric_frame['direction'] == 1]
xbins = self.mean_fric_frame['load_index'].max() + 1
sns.set_context(sns_context)
f, (ax1, ax2) = plt.subplots(nrows=1, ncols=2)
sns.regplot(x='N', y='F', data=p_dat, x_bins=xbins, ax=ax1)
sns.regplot(x='N', y='F', data=n_dat, x_bins=xbins, ax=ax2)
ax1.set_title("(+)")
ax2.set_title("(-)")
plt.tight_layout()
plt.show()
def view_correlations(corr_df, dftouse, y=False, filter=None, col_num=2):
if not y: # use dependent variable from first column of data frame
y = dftouse[dftouse.columns.values[0]]
# get the number of axes required
axes_num = len(corr_df)
axes_num = axes_num + 1 if is_prime(axes_num) else axes_num
row_num = axes_num / col_num
print row_num , col_num
# create the figure and axes for each plot
f, axes = plt.subplots(row_num, col_num, figsize=(30,30))
# generate plots for each independent variable
for ax, (x, corr) in zip(axes.ravel(),corr_df.iterrows()):
if filter == None or filter in x:
sns.regplot(x=dftouse[x], y=dftouse[y], ax=ax)
plt.show()
def createMatrixInteract(self, event):
dlg = RegressDialog(self.parent, "Matrix Interaction Plot")
log = wx.CheckBox(dlg, label="Logistic Fit?")
dlg.Add(log)
if dlg.ShowModal() == wx.ID_OK:
y, xs = dlg.GetValue()
log = log.GetValue()
data = self.parent.data[list(xs) + [y]]
df = data[list(xs)]
fig, axes = plt.subplots(nrows=len(xs), ncols=len(xs))
for i, l1 in enumerate(df):
for j, l2 in enumerate(df):
ax = axes[j, i]
ax.grid(False)
plt.subplot(ax)
if i == j:
sns.regplot(data[l1], data[y], ax=ax),
# would like to do logistic plot, but takes too long
elif i < j:
sns.interactplot(l1, l2, y, data, ax=ax, logistic=log,
cmap=settings["cmap"])
if i != 0 and j != 0:
ax.yaxis.set_visible(False)
if j != len(xs) - 1:
ax.xaxis.set_visible(False)
plt.show()
def fig_compareposteriors(posterior_a, posterior_b):
pbbetter = (np.array(posterior_b) > np.array(posterior_a)).mean()
agtb = [i for i, (a, b) in enumerate(zip(posterior_a, posterior_b))
if a > b]
bgta = [i for i, (a, b) in enumerate(zip(posterior_a, posterior_b))
if b > a]
fig, ax = plt.subplots(figsize=(6.5, 6.5))
ax = sns.regplot(np.array(posterior_a)[agtb], np.array(posterior_b)[agtb],
fit_reg=False, color=cola, marker='.')
ax = sns.regplot(np.array(posterior_a)[bgta], np.array(posterior_b)[bgta],
fit_reg=False, color=colb, marker='.')
ax.plot(0.04, 0.05, color='#222222', marker='X')
lim1, lim2 = 0, 0.12
ax.set_xlim(lim1, lim2)
ax.set_ylim(lim1, lim2)
ax.plot([lim1, lim2], [lim1, lim2], color=colb)
ax.text(0.07, 0.10, 'B better', color=colb)
ax.text(0.07, 0.095, '{:.1f}%'.format(100*pbbetter), color=colb)
ax.text(0.09, 0.07, 'A better', color=cola)
ax.text(0.09, 0.065, '{:.1f}%'.format(100-100*pbbetter), color=cola)
ax.set_xlabel('Conversion fraction layout A')
ax.set_ylabel('Conversion fraction layout B')
fig.savefig('img/compareposteriors.png', bbox_inches='tight')
def fig_linplot(data, x , y, aly_title, fig_save = True):
""" Plot correlations
Parameters
----------
data : pd.DataFrame
x,y : str
X and Y axis for the plot, valid column names of data
aly_title : str
fig_save : bool, optional
False if data should not be saved
"""
ff = file_folder_specs()
title = aly_title + 'for {} vs {}'.format(x, y)
sns.regplot(x ,y , data = data)
plt.title(title)
plt.xlim(0)
plt.ylim(0)
if fig_save:
_save_fig(title, ff['fig'])
plt.show()
plt.close()
def timePlotLine(data):
normalize = input("Would you like to normalize the y-axis? (y/n): ")
geneNamesDict = {}
for _, row in data.iterrows():
geneNamesDict[row['Gene']] = 1
data = data.pivot_table('Values', ['Sample'], ['Gene', 'Time'])
geneList = geneNamesDict.keys()
ylabel = input("What should the y-axis label be?: ")
counter = 1
for key in geneList:
plt.figure(counter)
tempTable = data[key]
tempTable = tempTable.T
tempTable = tempTable.dropna(axis=1, how='any')
if normalize == 'y':
tempTable = tempTable / np.amax(tempTable.values)
tempTable['Time'] = tempTable.index
tempTable = pd.melt(tempTable, id_vars='Time')[['Time','value']]
sns.regplot(x='Time',y='value',data=tempTable,scatter=True)
plt.title(key)
plt.ylabel(ylabel)
plt.xlabel('Time(min)')
counter += 1
plt.show()
def plot_against_y(self, function=None, y_margin=0.1, lim=10, context="talk"):
"""Where colour is squared error or some other var"""
# do linked plots here
cat, cont, time = cat_cont_time(self.df[self.vars_of_interest])
# cat = self.df.columns[self.df.dtypes=='category']
# cont = self.df.columns[self.df.dtypes=='float64']
# first continuous
cols = cat + cont + time
cols = cols[:10]
sns.set_context(context)
fig, axs = plt.subplots(nrows=1, ncols=len(cols), sharey=True)
for ax, col in zip(axs.flat, cols):
if col in cont:
sns.regplot(x=col, y=self.y, data=self.df, ax=ax)
# g = sns.lmplot(x="total_bill", y=self.y, data=self.df)
# then categorical
# fig, axs = plt.subplots(nrows=1, ncols=len(cat), sharey=True)
# for ax, col in zip(axs.flat, cat):
elif col in cat:
sns.violinplot(x=col, y=self.y, data=self.df, ax=ax)
else:
# plot timeseries
self.df([self.y, col]).plot()
y_min, y_max = self.df[self.y].min(), (self.df[self.y].max())
y_range = y_max - y_min
plt.ylim(y_min - y_margin * y_range, y_max + y_margin * y_range)
# g = sns.FacetGrid(self.df,col=self.df.columns[self.df.dtypes=='category'],row=self.y,sharey=True)
# g.map(sns.violinplot)
return fig
def plot_crbl_fit(model_df, rbh_df, hits_df, model_plot_fn, show=False,
figsize=(10,10)):
plt.style.use('seaborn-ticks')
with FigureManager(model_plot_fn, show=show,
figsize=figsize) as (fig, ax):
scatter_kws = {'s': 10, 'alpha':0.7}
scatter_kws['c'] = sns.xkcd_rgb['ruby']
scatter_kws['marker'] = 'o'
line_kws = {'c': sns.xkcd_rgb['red wine'],
'label':'Query Hits Regression'}
sample_size = min(len(hits_df), 10000)
sns.regplot('s_aln_len', 'E_s', hits_df.sample(sample_size), order=1,
label='Query Hits', scatter_kws=scatter_kws,
line_kws=line_kws, color=scatter_kws['c'], ax=ax)
scatter_kws['c'] = sns.xkcd_rgb['twilight blue']
scatter_kws['marker'] = 's'
sns.regplot('center', 'fit', model_df,
fit_reg=False, x_jitter=True, y_jitter=True, ax=ax,
label='CRBL Fit', scatter_kws=scatter_kws, line_kws=line_kws)
leg = ax.legend(fontsize='medium', scatterpoints=3, frameon=True)
leg.get_frame().set_linewidth(1.0)
ax.set_xlim(model_df['center'].min(), model_df['center'].max())
ax.set_ylim(0, max(model_df['fit'].max(), hits_df['E'].max()) + 50)
ax.set_title('CRBL Fit')
def plotExp(self,exp,myData):
plt.figure();
sns.regplot(exp[1]['xaxis'],exp[1]['yaxis'],data=myData);
plt.savefig("plots/static/%d.png" %settings.count);
plt.clf()
plt.close()
settings.count=settings.count+1;
def sim_regression(show=True):
"""Simulate a data set with one regressor (age) on both d' and c.
"""
intercepts = {'d': 1, 'c': 0}
betas = {'d': -0.005, 'c': 0.001}
errors = {'d': 0.05, 'c': 0.005}
reg = lambda p, y: intercepts[p] + betas[p] * y
nsubjects = 100
y = np.linspace(10, 90, 1000)
ages = np.random.randint(18, 80, size=nsubjects)
data = {
'age': ages,
'N': [50] * nsubjects,
'S': [50] * nsubjects
}
plt.figure(figsize=(15, 7.5))
for i, p in enumerate(['d', 'c'], 1):
plt.subplot(1, 2, i)
true_p = reg(p, ages) + norm.rvs(0, errors[p], nsubjects)
sb.regplot(ages, true_p, fit_reg=False, label='True values (regression + some error)')
plt.plot(y, reg(p, y), linewidth=2, label='True regression line')
plt.ylabel(p)
data['true_%s' % p] = true_p
simulations = np.asarray(
simulate(data['true_d'], data['true_c'], data['N'], data['S'])
)
data['F'], data['H'], data['M'], data['R'] = zip(*simulations)
data['mle_d'], data['mle_c'] = zip(*est_sdt(*zip(*simulations)))
df = pd.DataFrame(data)
df['subj'] = ['subj_%i' % i for i in df.index]
df.to_csv('02.OneContinuousAndOneDichotomousPredictor.csv')
ylabels = {'d': "$d^\prime$", 'c': "$c$"}
for i, p in enumerate(['d', 'c'], 1):
plt.subplot(1, 2, i)
sb.regplot(
'age', 'mle_%s' % p, df,
label='MLEs based on simulated data (%i trials per subject)' %
(data['N'][0] + data['S'][0])
)
plt.ylabel(ylabels[p])
plt.xlabel('Age (years)')
plt.xlim(10, 90)
if show is True:
print df
plt.legend()
plt.tight_layout(pad=0)
plt.savefig('fig1.png')
else:
return df
def scatter_plot(df,dep_var, indep_var,units):
seaborn.regplot(x=indep_var, y=dep_var, data=df, fit_reg=False)
#would be great to figure out how to remove '_cat'
plt.xlabel(indep_var)
plt.ylabel(dep_var + ", " + units)
plt.title("Scatterplot of " + dep_var + " versus " + indep_var)
plt.savefig(wd + "Scatterplot_" + dep_var + "_vs_"+ indep_var + '.png')
plt.close
def plot_prediction_error(name, clf, X, y):
plt.figure()
cv = KFold(X.shape[0], 5, shuffle=True)
predicted = cross_val_predict(clf, X, y, cv=cv)
print("%.3f = mean squared error" % mean_squared_error(y, predicted))
sns.regplot(x=y[:1000], y=predicted[:1000])
sns.axlabel("actual", "predicted")
plt.savefig("plot_validation_" + name + ".png")
def make_scatter_plot(explain, response):
seaborn.regplot(x=explain, y=response, fit_reg=True, data=df_combined)
plt.xlabel(str(explain))
plt.ylabel(str(response))
plt.title('Association between '+str(explain)+ ' and '+str(response))
plt.show()
print (scipy.stats.pearsonr(df_combined[explain], df_combined[response]))
def makeCorrPlot(truthCol, predCol, df, outBase, method, measure, logged=True):
plt.cla()
plt.clf()
measureName = "NO MEASURE NAME"
if measure == "tpm":
outFile = "{}_tpm_corr.pdf".format(outBase)
measureName = "TPM"
elif measure == "num_reads":
outFile = "{}_num_reads_corr.pdf".format(outBase)
measureName = "# fragments"
rv, pv = stats.spearmanr(df[truthCol], df[predCol])
corrText = "Spearman r = {0:.2f}".format(rv)
if (logged):
minLogVal = -2.5
smallVal = 1e-2
ax = plt.axes()
minVal = min(np.log10(df.loc[df[truthCol] > 0, truthCol].min()),
np.log10(df.loc[df[predCol] > 0, predCol].min()))
maxVal = max(np.log10(df.loc[df[truthCol] > 0, truthCol].max()),
np.log10(df.loc[df[predCol] > 0, predCol].max()))
sns.regplot(np.log10(df[truthCol]), np.log10(df[predCol]), df,
fit_reg=False, dropna=True, color=[0.7, 0.7, 0.7, 0.2],
ax=ax)
ax.set_xlabel("log(True {})".format(measureName))
ax.set_ylabel("log({} {})".format(method, measureName))
ax.set_xlim(minVal-0.5, maxVal+0.5)
ax.set_ylim(minVal-0.5, maxVal+0.5)
plt.figtext(0.15, 0.85, corrText)
else:
ax = plt.axes()
minVal = min(df[truthCol].min(), df[predCol].min())
maxVal = max(df[truthCol].max(), df[predCol].max())
sns.regplot(truthCol, predCol, df, fit_reg=False,
color=[0.7, 0.7, 0.7, 0.2], ax=ax)
ax.set_xlabel("True {}".format(measureName))
ax.set_ylabel("{} {}".format(method, measureName))
ax.set_xlim(minVal, maxVal)
ax.set_ylim(minVal, maxVal)
plt.figtext(0.15, 0.85, corrText)
# Get rid of axis spines
sns.despine()
plt.savefig(outFile)
def plot_time_effects(measure_DVs, melted_DVs, title=None):
f, (ax1,ax2) = plt.subplots(1, 2, figsize=(16,8))
for name in measure_DVs.columns[:-2]:
sns.regplot('hour', name, data=measure_DVs, lowess=True, label=name,
ax=ax1, scatter_kws={'s': 100, 'alpha': .4})
ax1.legend()
sns.boxplot('split_time', 'value', hue='variable', data=melted, ax=ax2)
if title:
plt.suptitle(title, fontsize=18)
plt.show()
df = df[df['date'] >= '2020-03-01'].reset_index()
df.drop('index', axis=1, inplace=True)
print(df.head())
plt.figure(figsize=(20, 10))
plt.bar(df.date, df['new_cases'], color='salmon')
ax = plt.gca()
for i, label in enumerate(ax.get_xaxis().get_ticklabels()):
if i % 7 != 0:
label.set_visible(False)
sns.regplot(x=df.index,
y='rolling_avg_week',
data=df,
order=16,
ci=None,
color='red')
plt.title('California COVID-19 New Cases By Day')
plt.xlabel('Date')
plt.ylabel('New Cases')
plt.show()
last_week = df.tail(7)['rolling_avg_week']
m = (last_week.iloc[6] - last_week.iloc[0]) / 6
b = last_week.iloc[6]
five_hundred = ceil((500 - b) / m)
print('Based on current weekly trends, it would take ' + str(five_hundred) +
' days until the average number of new daily cases in '
df=pd.DataFrame(np.random.rand(6,4),
index=['one','two','three','four','five','six'],
columns=[pd.Index(['A','B','C','D'],name='Genus')])
df.plot.bar()
df.plot.barh(stacked=True, alpha=0.5)
df
tips =pd.read_csv('C:/Users/barak/OneDrive/Documents/python/pydata-book-2nd-edition/examples/tips.csv')
######Seaborn
import seaborn as sns
tips['tip_pct']= tips['tip']/(tips['total_bill']-tips['tip'])
tips
sns.barplot(x='tip_pct',y='day',data=tips,orient='h')
sns.barplot(x='tip_pct',y='day',data=tips,orient='h', hue='time')
sns.set(style='whitegrid')
tips['tip_pct'].plot.density()
macrodata =pd.read_csv('C:/Users/barak/OneDrive/Documents/python/pydata-book-2nd-edition/examples/macrodata.csv')
######Seaborn
data=macrodata[['cpi','m1','tbilrate','unemp']]
trans_data=np.log(data).diff().dropna()
trans_data[-5:]
sns.regplot('m1','unemp',data=trans_data)
plt.title('Change in log %s Versus log %s' % ('m1','unemp'))
sns.pairplot(trans_data,diag_kind='kde',plot_kws={'alpha':0.2})
########
adding things
#We can use bar chart or pie chart to visualise the distribution of categorical variables.
fig = plt.figure(figsize=(15, 8))
for i, c in enumerate(categoricalVariables):
ax = plt.subplot(3, 3, i + 1)
sns.countplot(x=train[c])
fig.tight_layout()
plt.show()
train[continuousVariables].describe()
fig = plt.figure(figsize=(15, 5))
for i, c in enumerate(continuousVariables):
ax = plt.subplot(2, 2, i + 1)
sns.distplot(train[c].dropna())
fig.tight_layout()
plt.show()
fig = plt.figure(figsize=(15, 10))
for i, c in enumerate(categoricalVariables):
ax = plt.subplot(3, 3, i + 1)
sns.boxplot(x=train[c], y=train["count"])
fig.tight_layout()
#continuous variables
fig = plt.figure(figsize=(15, 10))
for i, c in enumerate(continuousVariables):
ax = plt.subplot(2, 2, i + 1)
sns.regplot(x=train[c], y=train["count"])
fig.tight_layout()
def regplot(data: pd.DataFrame, featX: str, featY: str) -> None:
fig, ax = plt.subplots()
sns.regplot(data[featX], data[featY], logistic=True, ax=ax)
sns.regplot(data[featX], data[featY], lowess=True, ax=ax)
fig.show()
def mantel(output_dir: str,
dm1: skbio.DistanceMatrix,
dm2: skbio.DistanceMatrix,
method: str = 'spearman',
permutations: int = 999,
intersect_ids: bool = False,
label1: str = 'Distance Matrix 1',
label2: str = 'Distance Matrix 2') -> None:
test_statistics = {'spearman': 'rho', 'pearson': 'r'}
alt_hypothesis = 'two-sided'
# The following code to handle mismatched IDs, and subsequently filter the
# distance matrices, is not technically necessary because skbio's mantel
# function will raise an error on mismatches with `strict=True`, and will
# handle intersection if `strict=False`. However, we need to handle the ID
# matching explicitly to find *which* IDs are mismatched -- the error
# message coming from scikit-bio doesn't describe those. We also need to
# have the mismatched IDs to display as a warning in the viz if
# `intersect_ids=True`. Finally, the distance matrices are explicitly
# filtered to matching IDs only because their data are used elsewhere in
# this function (e.g. extracting scatter plot data).
# Find the symmetric difference between ID sets.
ids1 = set(dm1.ids)
ids2 = set(dm2.ids)
mismatched_ids = ids1 ^ ids2
if not intersect_ids and mismatched_ids:
raise ValueError(
'The following ID(s) are not contained in both distance matrices. '
'This sometimes occurs when mismatched files are passed. If this '
'is not the case, you can use `intersect_ids` to discard these '
'mismatches and apply the Mantel test to only those IDs that are '
'found in both distance matrices.\n\n%s' %
', '.join(sorted(mismatched_ids)))
if mismatched_ids:
matched_ids = ids1 & ids2
# Run in `strict` mode because the matches should all be found in both
# matrices.
dm1 = dm1.filter(matched_ids, strict=True)
dm2 = dm2.filter(matched_ids, strict=True)
# Run in `strict` mode because all IDs should be matched at this point.
r, p, sample_size = skbio.stats.distance.mantel(dm1,
dm2,
method=method,
permutations=permutations,
alternative=alt_hypothesis,
strict=True)
result = pd.Series(
[method.title(), sample_size, permutations, alt_hypothesis, r, p],
index=[
'Method', 'Sample size', 'Permutations', 'Alternative hypothesis',
'%s %s' % (method.title(), test_statistics[method]), 'p-value'
],
name='Mantel test results')
table_html = q2templates.df_to_html(result.to_frame())
# We know the distance matrices have matching ID sets at this point, so we
# can safely generate all pairs of IDs using one of the matrices' ID sets
# (it doesn't matter which one).
scatter_data = []
for id1, id2 in itertools.combinations(dm1.ids, 2):
scatter_data.append((dm1[id1, id2], dm2[id1, id2]))
plt.figure()
x = 'Pairwise Distance (%s)' % label1
y = 'Pairwise Distance (%s)' % label2
scatter_data = pd.DataFrame(scatter_data, columns=[x, y])
sns.regplot(x=x, y=y, data=scatter_data, fit_reg=False)
plt.savefig(os.path.join(output_dir, 'mantel-scatter.svg'))
context = {
'table': table_html,
'sample_size': sample_size,
'mismatched_ids': mismatched_ids
}
index = os.path.join(TEMPLATES, 'mantel_assets', 'index.html')
q2templates.render(index, output_dir, context=context)
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
import statsmodels.formula.api as smf
import statsmodels.api as sm
from scipy.stats import linregress
import seaborn as sns
allData = pd.read_csv(r'C:\Users\nuran\Desktop\Senior_Project\All_data.csv',
skiprows=0,
delimiter=',')
x = allData['Independence_00']
y = allData['Response_Rate_00'] #y
plt.figure(figsize=(10, 10))
sns.regplot(x, y)
plt.plot([x], [y], 'o', label='Indepedence', color='yellow', markersize='3')
plt.title('Linear Regression Analysis: Response Rate & Independence for 2000')
plt.xlabel('Independence', color='#1C2833')
plt.ylabel('Response Rate')
plt.show()
#
# clean code
#
# clean code
len(diff_hESC_endo_ncRNA[diff_hESC_endo_ncRNA["qval_hESC_endo"] < 0.05])
# In[103]:
len(diff_hESC_endo_ncRNA[diff_hESC_endo_ncRNA["qval_hESC_endo"] < 0.05]
["gene_name"].unique())
# In[104]:
fig = plt.figure(figsize=(1.5, 1.75))
g = sns.regplot(x="endo_hESC_log2fc",
y="qval_log10_hESC_endo",
data=diff_hESC_endo_ncRNA,
fit_reg=False,
color="firebrick",
scatter_kws={
"s": 8,
"edgecolors": "white",
"linewidths": 0.5
})
plt.xlabel("log2(endoderm/hESC)")
plt.ylabel("negative log10 q value")
plt.ylim((-0.1, 4))
plt.xlim((-8.5, 8.5))
plt.axhline(y=-np.log10(0.05), linestyle="dashed", color="black", linewidth=1)
#plt.title("volcano plot for ncRNAs in endoderm vs. hESCs\n(n=%s)" % (len(diff_hESC_endo_ncRNA)))
plt.savefig("Fig2E_1.pdf", bbox_inches="tight", dpi="figure")
# In[105]:
print(lm.summary()) # In[18]: # regression statistics of rest of world sales lm = smf.ols(formula = "Global_Sales ~ Other_Sales", data = df).fit() print(lm.summary()) # In[22]: # regression plot of North American vs global sales sns.regplot(x = "NA_Sales", y = "Global_Sales", data = df) # In[23]: # regression plot of European vs global sales sns.regplot(x = "EU_Sales", y = "Global_Sales", data = df) # In[24]: # regression plot of Japanese vs global sales sns.regplot(x = "JP_Sales", y = "Global_Sales", data = df)
import seaborn as sns
from matplotlib import pyplot as plt
import pandas as pd
sns.set_context("poster")
sns.axes_style()
sns.despine()
from scipy import stats
df = pd.read_csv('data.csv')
sns.lmplot(x='frame', y='x_position', data=df, fit_reg=True)
# get coeffs of linear fit
slope, intercept, r_value, p_value, std_err = stats.linregress(
df['frame'], df['x_position'])
# use line_kws to set line label for legend
ax = sns.regplot(
x="frame",
y="x_position",
data=df,
line_kws={'label': "y={0:.1f}x+{1:.1f}".format(slope, intercept)})
# plot legend
ax.legend()
sns.despine()
plt.show()
ax.get_figure().savefig("output.png")
count = count + 1
plt.show()
# Plot high correlation attributes - PLOTS #3 - GOOD
fig = plt.figure(figsize=(14,60))
col = 3
row = int(len(df_corr.Attributes)/col)
count = 1
for i, j in zip(df_plot.Attributes,df_plot.Correlation):
fig.add_subplot(row, col, count)
plt.title('Salinity vs {} (corr = {:.4f})\nnormalized distribution'.format(i,j))
#plt.xlim(-4,4)
sns.regplot(x=df_sample[i],y="Salnty",data=df_sample,order=2, scatter_kws={'alpha':0.25},color='green');
count = count + 1
plt.show()
#===============================================
#===============================================
# PLOT ALL COLUMNS IN CORR - not good
#===============================================
# Plot high correlation attributes - PLOTS #1 - CRAP
fig = plt.figure(figsize=(12,60))
plotNum = 1 # initialize plot number
#for i in df_high.columns.drop(['Salnty','R_SALINITY']):
for i, j in zip(df_high.Attributes,df_high.Correlation):
import seaborn as sns
from pydataset import data
import pandas as pd
import matplotlib.pyplot as plt
from env import host, password, user
iris = data('iris')
sns.distplot(iris['Petal.Length'])
sns.regplot(x='Petal.Length', y='Petal.Width', data=iris) # Yes
sns.relplot(x='Sepal.Length', y='Sepal.Width', data=iris, hue='Species'
) # Probably? Many edge cases between versicolor and virginica
sns.pairplot(
iris
) # It looks like setosa is easy to identify regardless of feature; I think petal width/length look like the best pair of features by which to distinguish versicolor and virginica, but it's still an imperfect metric.
anscombe = sns.load_dataset('anscombe')
anscombe.groupby('dataset').describe()
sns.relplot(x='x', y='y', data=anscombe, col='dataset')
insectsprays = data('InsectSprays')
sns.boxplot(data=insectsprays, y='count', x='spray')
swiss = data('swiss')
swiss['is_catholic'] = swiss['Catholic'] > 80
# given (hh:mm:ss)_1 and (hh:mm:ss)_2. find the difference in seconds
print(
sum([(60**((5 - i) % 3)) * int(input()) * int((i // 3 - 0.5) * 2.0)
for i in range(6)]))
import seaborn as sns
ax = sns.regplot(x='input', y='output', data=df, color='green', marker='+')
def pairgrid_plots(stats,
dims,
statop,
season=None,
scenario=None,
period=None):
season_ren = {
'full': 'annual',
's1': 'spring',
's2': 'summer',
's3': 'autumn',
's4': 'winter',
'FULL': 'annual',
'MAM': 'spring',
'JJA': 'summer',
'SON': 'autumn',
'DJF': 'winter'
}
stat_ren = {'timmean': 'mean', 'timvar': 'variance'}
exp_ren = {'timmean': 'mean', 'timvar': 'variance'}
d = dims['inv']
op = d[2][statop]
m = {}
exps = [
i for i in range(len(dims['exps']))
if ((period is None) or period in dims['exps'][i]) and (
(scenario is None) or scenario in dims['exps'][i])
]
seasons = [i for i in range(len(dims['seasons']))
] if season is None else [d[0][season]]
#scenarios = [i for i in range(len(dims['exps'])) if scenario in dims['exps'][i]] if scenario else []
#periods = [i for i in range(len(dims['exps'])) if period in dims['exps'][i]] if period else []
#print(dims['exps'])
#print('scen', [dims['exps'][i] for i in scenarios])
#print('peri', [dims['exps'][i] for i in periods])
#print(seasons)
#exit()
'''
print('Building DataFrame')
for s in seasons:
for e in exps:
tas = stats[s][e][op][d[3]['tas']]
pr = stats[s][e][op][d[3]['pr']]
exp_label = dims['exps'][e]
season_label = season_ren[dims['seasons'][s]]
#stat_label = stat_ren[statop]
name = '%s %s %s' % ('tas', season_label, exp_label)
print(name)
m[name] = tas
name = '%s %s %s' % ('pr', season_label, exp_label)
m[name] = pr
print('Define DataFrame')
#df = pd.DataFrame(m)
#print(df)
#return
g = sns.PairGrid(df)
g.map_upper(sns.regplot)
g.map_lower(sns.kdeplot, cmap = 'Blues_d')
g.map_diag(sns.kdeplot, lw = 3, legend = True);
plt.show()
'''
fig = plt.figure(figsize=(18, 9))
n = 0
#cols = seasons if season is None else
pos = [len(exps), len(seasons), n]
print('exps', [dims['exps'][i] for i in exps], pos)
for e in exps:
for s in seasons:
# plot one week pr / tas
n += 1
pos[2] = n
ax = fig.add_subplot(*pos)
tas = stats[s][e][op][d[3]['tas']]
pr = stats[s][e][op][d[3]['pr']] * (24 * 60 * 60)
exp_label = dims['exps'][e]
season_label = season_ren[dims['seasons'][s]]
tas_name = '%s %s %s' % ('tas', season_label, exp_label)
pr_name = '%s %s %s' % ('pr', season_label, exp_label)
print(tas_name)
df = pd.DataFrame({tas_name: tas, pr_name: pr})
sns.regplot(data=df, x=tas_name, y=pr_name, fit_reg=True, ax=ax)
plt.show()
filewriter.add_summary(summ_buf, i)
else:
train_loss, _ = sess.run([loss, train_op], feed_dict=feed_dict)
if min_loss is None or train_loss < min_loss:
min_loss = train_loss
table.add_row([path, min_loss, w.eval(), b.eval()])
# As we can see, 'ds2.csv' has the lowest loss, and thus contains the most linear data, 'ds3.csv' coming a distant second. The values of w and b are shown in the table.
# In[6]:
print(table)
# As we can see, the plots show that `ds2.csv` is the most linear.
# In[8]:
import seaborn as sb
import matplotlib.pyplot as plt
for path in paths:
d = pd.read_csv(path, names=['x', 'y'])
m1 = np.max(d['x'])
x = np.array(d['x'])
y = np.array(d['y'])
m2 = np.max(d['y'])
sb.regplot((x / m1), (y / m2))
plt.show()
# In[ ]:
import matplotlib.pyplot as plt
import seaborn as sns
titanic = sns.load_dataset('titanic')
# 스타일 테마 설정 (5가지: darkgrid, whitegrid, dark, white, ticks)
sns.set_style('darkgrid')
# 그래프 객체 생성 (figure에 2개의 서브 플롯을 생성)
fig = plt.figure(figsize=(15, 5))
ax1 = fig.add_subplot(1, 2, 1)
ax2 = fig.add_subplot(1, 2, 2)
# 그래프 그리기 - 선형회귀선 표시(fit_reg=True)
sns.regplot(
x='age', # x축 변수
y='fare', # y축 변수
data=titanic, # 데이터
ax=ax1) # axe 객체 - 1번째 그래프
# 그래프 그리기 - 선형회귀선 미표시(fit_reg=False)
sns.regplot(
x='age',
y='fare',
data=titanic,
ax=ax2, # axe 객체 - 2번째 그래프
fit_reg=False) # 회귀선 미표시
plt.show()
def plot_candidate_codons(env, df, codons, cmap=None):
# type: (Environment, pd.DataFrame, List[str]) -> None
fig, ax = plt.subplots()
from sbsp_viz.colormap import ColorMap as CM
for c in sorted(codons):
seaborn.regplot(df["GC"].astype(float).values,
df[c].astype(float).values,
label=c,
lowess=True,
scatter_kws={
"s": 5,
"alpha": 0.1
},
color=cmap[c])
ax.set_ylim([-0.05, 1.05])
ax.set_ylabel("Probability")
ax.set_xlabel("GC")
leg = ax.legend()
for lh in leg.legendHandles:
lh.set_alpha(1)
plt.show()
# bacteria vs archaea
fig, axes = plt.subplots(1, 2, sharex="all", sharey="all")
for t, ax in zip(["Bacteria", "Archaea"], axes.ravel()):
df_tmp = df[df["Type"] == t]
for c in sorted(codons):
seaborn.regplot(df_tmp["GC"].astype(float).values,
df_tmp[c].astype(float).values,
label=c,
lowess=True,
scatter_kws={
"s": 5,
"alpha": 0.1
},
ax=ax,
color=cmap[c])
ax.set_ylim([-0.05, 1.05])
ax.set_ylabel("Probability")
ax.set_xlabel("GC")
ax.set_title(t)
leg = ax.legend()
for lh in leg.legendHandles:
lh.set_alpha(1)
plt.show()
# group
fig, axes = plt.subplots(2, 2, sharex="all", sharey="all")
for t, ax in zip(list("ABCD"), axes.ravel()):
df_tmp = df[df["GENOME_TYPE"] == t]
for c in sorted(codons):
seaborn.regplot(df_tmp["GC"].astype(float).values,
df_tmp[c].astype(float).values,
label=c,
lowess=True,
scatter_kws={
"s": 5,
"alpha": 0.1
},
ax=ax,
color=cmap[c])
ax.set_ylim([-0.05, 1.05])
ax.set_ylabel("Probability")
ax.set_xlabel("GC")
ax.set_title(t)
leg = ax.legend()
for lh in leg.legendHandles:
lh.set_alpha(1)
plt.show()
print(
str(RMes.shape[0] - RMes[RMes['EC taken'] >= 120].shape[0]) +
' RMes students removed with <120ECs')
RMes_filtered = RMes[RMes['EC taken'] >= 120]
# 3a) Checking normality
stats.kstest(RMes_filtered['thesis_grades'], 'norm')
stats.kstest(RMes_filtered['EC taken'], 'norm')
# 3b) Spearmans
stats.spearmanr(RMes_filtered['thesis_grades'],
RMes_filtered['EC taken']) # rs = 0.0572, p = 0.520
fig, ax = plt.subplots(figsize=(45, 24))
sns.regplot(RMes_filtered['EC taken'],
RMes_filtered['thesis_grades'],
color='black',
y_jitter=0.05)
plt.xlabel('ECs taken', fontsize=35)
plt.ylabel('Thesis Grade', fontsize=35)
plt.title('ECs against thesis grade (RMes)', fontsize=35)
sns.set_style('darkgrid')
plt.xticks(fontsize=25)
plt.yticks(fontsize=25)
ax.set_ylim(5, 10.1)
ax.set_xlim(119, 156)
ax.text(145, 5.2, 'rs = 0.0572, p = 0.520, n = 129', fontsize=50)
plt.show()
# 4a) MSc all spec
stats.kstest(MSc_filtered['thesis_grades'], 'norm')
stats.kstest(MSc_filtered['EC taken'], 'norm')
data2 = pd.DataFrame({
'Standard Reading Level': [mean_a+bwo],
'CDF': [heights[0]]
})
data1 = pd.DataFrame({
'Standard Reading Level': x_sub_set,
'CDF': std_plot_ind
})
legend_properties = {'weight':'bold','size':8}
ax = sns.regplot(data=benchmarks, x="benchmarks", y="CDF", fit_reg=False, marker="o", color="green")
#bbox_props = dict(boxstyle="rarrow", fc=(0.8,0.9,0.9), ec="b", lw=2)
#t = ax.text(0, 0, "Direction", ha="center", va="center", rotation=90,
# size=15,
# bbox=bbox_props)
#import pdb; pdb.set_trace()
#bmark_heights.reverse()
for i in bmark_heights:
print(i)
#import pdb
#pdb.set_trace()
cnt=0
for i,j,k in zip(bmark_stats_items[0:-1],bmark_heights[0:-1],categories):
df[df['Status'].notnull()]['Status'].value_counts().plot(kind = 'pie', autopct='%1.1f%%')
#plt.title('status Partitions')
#plt.show()
print(df[['Status', 'accuracy']][df.Status.notnull()].groupby('Status').mean())
df[df['Status'] != 'None'].boxplot(column = ['accuracy'], by = ['Status'])
plt.title('')
plt.show()
ax = sns.boxplot(x="Status", y="accuracy", hue="Status",data=df, linewidth=2.5)
plt.show()
X = np.array(d1)
y=df['Status'] = df['Status'].map({'completed': 1, 'parsed with error': 2,'drop case': 0})
sns.regplot(X, y, data=df, fit_reg=False)
plt.show()
import numpy as np
import matplotlib.pyplot as plt
# Create data
import seaborn as sns
import matplotlib.pyplot as plt
carrier_count = df['accuracy'].value_counts()
sns.set(style="darkgrid")
sns.barplot(carrier_count.index, carrier_count.values, alpha=0.9)
plt.title('Frequency Distribution of Carriers')
plt.ylabel('Number of Occurrences', fontsize=12)
plt.xlabel('accuracy', fontsize=12)
(sns.factorplot(x="SES",hue="Gender",y="Proportion who chooses\neach career group",
data=spanish_data.rename(columns={"value":"Proportion who chooses\neach career group"}),
col="Field",
legend_out=False,
order=["Low","High"],col_wrap=4)
)
# %%
plt.close()
target="loggdppc"
merged_all.assign(Engistem=lambda x: x.hy_f_engi/x.hy_f_STEM)
#merged_all.query("Nrrent<20").plot.scatter("loggdppc","Engistem")
(merged_all.groupby("Country").mean().pipe(lambda x: x.plot
.scatter(target,"Engistem",s=x["pop"].pipe(lambda i: np.sqrt(i)),
c=x["Nrrent"],cmap="viridis")
))
sns.regplot(target,"Engistem",data=merged_all.groupby("Country").mean().query("pop>3000"),lowess=True,scatter=False,ax=plt.gca())
plt.ylabel("% female Engineering / % female STEM")
plt.xlabel("SIGI (0=less legal discrimination)")
# %%
pa="Reds"
pal=sns.palettes.color_palette(pa,len(k))
k=merged_all.query("loggdppc<9.5")
plt.close()
#sns.set_palette(pa,len(k))
sns.set_palette( "deep")
plt.figure()
i=0
jp.joyplot(k,column="hy_f_STEM",by="TIME")
for name,group in k.groupby("TIME"):
#sns.kdeplot(group.hy_f_STEM,ax=plt.gca(),label=name)
plt.axvline(group.hy_f_STEM.mean(),c=pal[i],ymax=0.5)
plt.ylabel('Number of Super Bowls')
plt.show()
# Display the closest game(s) and biggest blowouts
print(super_bowls[super_bowls['difference_pts'] == 1])
print(super_bowls[super_bowls['difference_pts'] >= 35])
## Do blowouts translate to lost viewers?
# Join game and TV data, filtering out SB I because it was split over two networks
games_tv = pd.merge(tv[tv['super_bowl'] > 1], super_bowls, on='super_bowl')
# Import seaborn
import seaborn as sns
# Create a scatter plot with a linear regression model fit
sns.regplot(x="difference_pts", y="share_household", data=games_tv)
## Viewership and the ad industry over time
# Create a figure with 3x1 subplot and activate the top subplot
plt.subplot(3, 1, 1)
plt.plot(games_tv.super_bowl, games_tv.avg_us_viewers, color='#648FFF')
plt.title('Average Number of US Viewers')
# Activate the middle subplot
plt.subplot(3, 1, 2)
plt.plot(games_tv.super_bowl, games_tv.rating_household, color='#DC267F')
plt.title('Household Rating')
# Activate the bottom subplot
plt.subplot(3, 1, 3)
plt.plot(games_tv.super_bowl, games_tv.ad_cost, color='#FFB000')
sns.distplot(colValues, bins=7, kde=False, color='b')
plt.title(colName)
plt.ylabel(colName)
plt.xlabel('Bins')
plt.show()
# scatterplots
# plot Sscatterplot
print('\n*** Scatterplot ***')
colNames = df.columns.tolist()
colNames.remove(depVars)
print(colName)
for colName in colNames:
colValues = df[colName].values
plt.figure()
sns.regplot(data=df, x=depVars, y=colName, color= 'b', scatter_kws={"s": 5})
plt.title(depVars + ' v/s ' + colName)
plt.show()
# class count plot
# change as required
colNames = ["CHAS","RAD"]
print("\n*** Distribution Plot ***")
for colName in colNames:
plt.figure()
sns.countplot(df[colName],label="Count")
plt.title(colName)
plt.show()
################################
def plot_mev_miv(df_radiomics):
"""
Plot a 3-subplot of pav vs eav, subcapsular and chemo
:param df_radiomics:
:return:
"""
font = {'family': 'DejaVu Sans', 'size': 18}
matplotlib.rc('font', **font)
df = pd.DataFrame()
df['PAV'] = df_radiomics['Predicted_Ablation_Volume']
df['EAV'] = df_radiomics['Ablation Volume [ml]']
df['Energy (kJ)'] = df_radiomics['Energy [kj]']
df['MWA Systems'] = df_radiomics['Device_name']
df['MIV'] = df_radiomics['Inner Ellipsoid Volume']
df['MEV'] = df_radiomics['Outer Ellipsoid Volume']
df['MEV-MIV'] = df['MEV'] - df['MIV']
df['R(EAV:PAV)'] = df['EAV'] / df['PAV']
fig, ax = plt.subplots(figsize=(12, 12))
sns.distplot(df['Energy (kJ)'],
hist_kws={
"ec": 'black',
"align": "mid"
},
axlabel='Energy',
ax=ax)
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures",
'Energy_distribution_' + timestr + '.png')
plt.savefig(figpath, bbox_inches='tight', dpi=300)
plt.close()
# drop outer volumes larger than 150 because they are probably erroneous
df = df[df['MEV'] < 150]
# drop the rows where MIV > MEV
# since the minimum inscribed ellipsoid (MIV) should always be smaller than the maximum enclosing ellipsoid (MEV)
df = df[df['MEV-MIV'] >= 0]
min_val = int(min(df['MEV-MIV']))
max_val = int(max(df['MEV-MIV']))
print('Min Val Mev-Miv:', min_val)
print('Max Val Mev-Miv:', max_val)
print('nr of samples for mev-miv:', len(df))
# %% histogram MEV-MIV
fig, ax = plt.subplots(figsize=(12, 12))
sns.distplot(
df['MEV-MIV'],
color=sns.xkcd_rgb["reddish"],
hist_kws={
"ec": 'black',
"align": "mid"
},
axlabel='Distribution of Ablation Volume Irregularity (MEV-MIV) (mL)',
ax=ax)
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures",
'MEV-MIV_distribution_' + timestr + '.png')
plt.savefig(figpath, bbox_inches='tight', dpi=300)
plt.close()
fig1, ax1 = plt.subplots(figsize=(12, 12))
sns.distplot(df['MEV'],
color=sns.xkcd_rgb["reddish"],
hist_kws={"ec": 'black'},
axlabel='MEV',
ax=ax1)
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures", 'MEV_distribution_' + timestr + '.png')
plt.savefig(figpath, bbox_inches='tight', dpi=300)
plt.close()
fig1, ax2 = plt.subplots(figsize=(12, 12))
sns.distplot(df['MIV'],
color=sns.xkcd_rgb["reddish"],
hist_kws={"ec": 'black'},
axlabel='MIV',
ax=ax2)
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures", 'MIV_distribution_' + timestr + '.png')
plt.savefig(figpath, dpi=300)
plt.close()
fig1, ax3 = plt.subplots(figsize=(12, 12))
sns.distplot(df['EAV'],
color=sns.xkcd_rgb["reddish"],
hist_kws={"ec": 'black'},
axlabel='EAV',
ax=ax3)
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures", 'EAV_distribution_' + timestr + '.png')
plt.savefig(figpath, dpi=300)
plt.close()
fig1, ax4 = plt.subplots(figsize=(12, 12))
sns.distplot(df['PAV'],
color=sns.xkcd_rgb["reddish"],
hist_kws={"ec": 'black'},
axlabel='PAV',
ax=ax4)
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures", 'PAV_distribution_' + timestr + '.png')
plt.savefig(figpath, dpi=300)
plt.close()
# %% R (EAV:PAV) on y-axis and MEV-MIV on the x-axis
fig1, ax5 = plt.subplots(figsize=(12, 12))
slope, intercept, r_square, p_value, std_err = stats.linregress(
df['R(EAV:PAV)'], df['MEV-MIV'])
print('p-val mev miv energy:', p_value)
print()
p = sns.regplot(y="R(EAV:PAV)",
x="MEV-MIV",
data=df,
scatter_kws={
"s": 100,
"alpha": 0.5
},
color=sns.xkcd_rgb["reddish"],
line_kws={'label': r'$r = {0:.2f}$'.format(r_square)},
ax=ax5)
plt.xlabel('MEV-MIV (mL)')
plt.legend()
timestr = time.strftime("%H%M%S-%Y%m%d")
figpath = os.path.join("figures",
'Ratio_EAV-PAV_MEV-MIV_difference_' + timestr)
plt.savefig(figpath, dpi=300, bbox_inches='tight')
plt.close()
weighted_ratio = [item[3] for item in data_city]
categories =[item[4] for item in data_city]
category_count=[item[5] for item in data_city]
data_city = {"city" : city, "review_count": review_count, "stars":stars, "weighted_ratio":weighted_ratio,"categories":categories,"category_count":category_count}
data_city=pd.DataFrame(data_city)
city_business_reviews = data_city[['city', 'review_count', 'stars']].groupby(['city']).agg({'review_count':'sum','stars': 'mean'}).sort_values(by='review_count', ascending=False)
city_business_reviews['review_count'][0:20].plot(kind='bar', stacked=False, figsize=[10,10],colormap='winter')
plt.title('Top 20 cities by reviews')
city_weighted_ratio =data_city[['city', 'weighted_ratio']].groupby(['city']).agg({'weighted_ratio': 'sum'}).sort_values(by='weighted_ratio', ascending=False)
city_weighted_ratio['weighted_ratio'][0:20].plot(kind='bar', stacked=False, figsize=[10,10],colormap='summer')
plt.title('Top 20 cities by Weighted Rating')
import seaborn as sns
sns.regplot(x=data_city["stars"], y=data_city["category_count"], fit_reg=False)
categories_data=spark.read.csv("categories.csv", header=True)
categories =categories_data.withColumn("stars", categories_data["stars"].cast(DoubleType()))
categories =categories.withColumn("review_count", categories_data["review_count"].cast(DoubleType()))
category=categories.select("city","categories","state","stars","review_count").collect()
city = [item[0] for item in category]
categories = [item[1] for item in category]
state = [item[2] for item in category]
stars = [item[3] for item in category]
review_count=[item[4] for item in category]
category = {"city" : city, "categories": categories, "state":state, "stars":stars,"review_count":review_count}
df=pd.DataFrame(category)
ax1 = plt.subplot(221)
ax1 = sns.violinplot(x="state", y="pledge_log", data=df_kick, palette="hls")
ax1.set_xticklabels(ax1.get_xticklabels(), rotation=45)
ax1.set_title("Understanding the Pledged values by state", fontsize=15)
ax1.set_xlabel("State Description", fontsize=12)
ax1.set_ylabel("Pledged Values(log)", fontsize=12)
ax2 = plt.subplot(222)
ax2 = sns.violinplot(x="state", y="goal_log", data=df_kick)
ax2.set_xticklabels(ax2.get_xticklabels(), rotation=45)
ax2.set_title("Understanding the Goal values by state", fontsize=15)
ax2.set_xlabel("State Description", fontsize=12)
ax2.set_ylabel("Goal Values(log)", fontsize=12)
ax0 = plt.subplot(212)
ax0 = sns.regplot(x="goal_log", y="pledge_log", data=df_kick, x_jitter=False)
ax0.set_title("Better view of Goal x Pledged values", fontsize=15)
ax0.set_xlabel("Goal Values(log)")
ax0.set_ylabel("Pledged Values(log)")
ax0.set_xticklabels(ax0.get_xticklabels(), rotation=90)
plt.show()
# <h2>Analysing further the CAaegorys: </h2>
# - Sucessful category's frequency
# - failed category's frequency
# - General Goal Distribuition by Category
# In[10]:
main_cats = df_kick["main_category"].value_counts()
main_cats_failed = df_kick[df_kick["state"] ==
X2_test = sc_X.transform(X_test)
# adsaasd
# X_sm = sm.add_constant(X)
# model = sm.OLS(y,X_sm)
# print(model.fit().summary())
lm1 = LinearRegression()
lm1.fit(X_train, y_train)
lm1_pred = lm1.predict(X_test)
print('Linear Regression Performance:')
print('MAE:', metrics.mean_absolute_error(y_test, lm1_pred))
print('RMSE:', np.sqrt(metrics.mean_squared_error(y_test, lm1_pred)))
print('R2_Score: ', metrics.r2_score(y_test, lm1_pred))
fig = plt.figure(figsize=(8, 5))
sns.regplot(y_test, lm1_pred, color='g')
plt.xlabel('COA')
plt.ylabel('Predictions')
plt.title('LinearRegression Prediction Performance ')
plt.grid()
plt.show()
# print('Estimated coefficients for the linear regression: ',lm1.coef_)
# print('Independent term: ', lm1.intercept_)
# import pickle
# filename = 'LinearRegression.sav'
# pickle.dump(lm1, open(filename, 'wb'))
# # load the model from disk
# loaded_model = pickle.load(open(filename, 'rb'))
# result = loaded_model.score(X_test, Y_test)
# print(result)
def split_timeseries_figures(in_frames,
names,
split_at=PRISM_DATE,
same_plot=True,
**kwargs):
"""
Takes the input data and creates a plot similar to figure 4a in the paper.
:param dataframes: An iterable of 2 pandas data frames with the dates (dtype=PeriodIndex) as index and views as only column
:param names: Names for the incoming data frames (neede for the legend)
:param split_at: The date at which the data shall be split
:param same_plot: If set false, a subplot will be created for each dataframe in in_frames. If true, they will be plotted on the same axis.
:return: Plots the figure
"""
# Default values that can be changed
title = kwargs.get('title', '')
figsize = kwargs.get('figsize', [18, 6])
keyword = kwargs.get('keyword', 'views')
sharey = kwargs.get('sharey', True)
show_legend = kwargs.get('legend', True) and same_plot
# Make sure we can iterate over the input argument to get a constant behavior, even if there is only 1df given.
if isinstance(in_frames, pd.DataFrame):
in_frames = [in_frames]
if isinstance(names, str):
names = [names]
assert len(names) == len(
in_frames
), "{} dataframes but {} names specified. This should be equal".format(
len(in_frames), len(names))
nr_subplots = len(in_frames)
same_plot = True if nr_subplots == 1 else same_plot # Remove useless specification of 'separate plots' if there is only 1 df
dfs_to_plot = []
for in_frame in in_frames:
# Prepare the dataframe for seaborn (https://stackoverflow.com/questions/52112979/having-xticks-to-display-months-in-a-seaborn-regplot-with-pandas)
# Seaborn has issues handling datetimes, so for the computation they are transformed to integers before transforming them back for the labelling later on.
# Matplotlib provides the necessary functionality.
dataframe = in_frame.copy()
dataframe.index = dataframe.index.to_timestamp()
dataframe['date_ordinal'] = mdates.date2num(dataframe.index)
dfs_to_plot.append(dataframe)
# Some color definition for plotting and the legend
if 'colors' in kwargs:
colors = kwargs['colors']
else:
colors = {}
cmap = cm.get_cmap(kwargs.get('cmap', 'Set1'))
cmap_colors = cmap.colors
for i, name in enumerate(names):
colors[name] = cmap_colors[i % len(cmap_colors)]
colors['Prism Disclosure, 6/6/2013'] = 'red'
# Starting to build the actual plot
if same_plot:
fig, ax = plt.subplots(figsize=figsize)
show_every_nth_month = 1 # There is enough space for every month to be displayed
else:
COLS = math.ceil(math.sqrt(nr_subplots))
ROWS = math.ceil(nr_subplots / COLS)
fig, axs = plt.subplots(ncols=COLS,
nrows=ROWS,
sharex=True,
sharey=sharey,
figsize=figsize)
show_every_nth_month = COLS # It gets tight if we display every month
for i, dataframe in enumerate(dfs_to_plot):
# First some axes unpacking. Numpy has an ugly feature of changing the depth of the list storing the axes, so lets unpack them
if not same_plot:
if ROWS == 1:
ROW = 0
COL = i
ax = axs[COL]
else:
COL = i % COLS
ROW = i // COLS
ax = axs[ROW][COL]
before = dataframe.loc[dataframe.index < split_at]
after = dataframe.loc[dataframe.index >= split_at]
sns.regplot(x='date_ordinal',
y=keyword,
data=before,
ax=ax,
color=colors[names[i]],
scatter_kws={
'color': colors[names[i]],
's': 30
},
line_kws={'color': colors[names[i]]})
sns.regplot(x='date_ordinal',
y=keyword,
data=after,
ax=ax,
color=colors[names[i]],
scatter_kws={
'color': colors[names[i]],
's': 30
},
line_kws={'color': colors[names[i]]})
ax.set(xlabel='', ylabel=''
) # Per default, we do not really want a label on every subplot
if not show_legend:
ax.set_title(names[i]) # Some minimum information should be there
# Tune the visuals
ax.set_xlim(dataframe['date_ordinal'].min() - 15,
dataframe['date_ordinal'].max() + 15) # 15 days offset
ax.vlines(mdates.date2num(split_at),
0,
1,
color=colors['Prism Disclosure, 6/6/2013'],
transform=ax.get_xaxis_transform(),
label=split_at)
if (not same_plot) and (COL == 0) and (not sharey):
ax.set_ylim(dataframe[keyword].min() * 0.9,
dataframe[keyword].max() *
1.1) # Assumes there are no negative values
ax.set_ylabel(keyword)
if (not same_plot) and (ROW + 1 == ROWS):
# As mentioned above, the date was transformed to integers for the sake of plotting it using seaborn.
# Now, they have to be transformed back to have nice x-Axis labels that are human-readable
loc = mdates.MonthLocator(interval=show_every_nth_month)
ax.xaxis.set_major_locator(loc)
ax.xaxis.set_major_formatter(mdates.AutoDateFormatter(loc))
# Formatting and Optics
fig.patch.set_facecolor('lightgrey')
fig.suptitle(title)
# Axis settings
if same_plot:
ax.set_xlabel('Month / Year')
ax.set_ylabel(keyword)
# As mentioned above, the date was transformed to integers for the sake of plotting it using seaborn.
# Now, they have to be transformed back to have nice x-Axis labels that are human-readable
loc = mdates.MonthLocator(interval=show_every_nth_month)
ax.xaxis.set_major_locator(loc)
ax.xaxis.set_major_formatter(mdates.AutoDateFormatter(loc))
fig.autofmt_xdate(rotation=60)
if show_legend:
# Add a custom legend
legend_patches = []
for entry, c in colors.items():
legend_patches.append(mpatches.Patch(color=c, label=entry))
# legend_patches.append(mpatches.Patch(color='lightgrey', label='95% Confidence Interval'))
font = FontProperties()
font.set_size('large')
plt.legend(handles=legend_patches,
title='Legend',
bbox_to_anchor=(0, 0),
loc='lower left',
prop=font,
ncol=math.ceil(math.sqrt(nr_subplots)),
fancybox=True,
shadow=True)
mySession.loc[mySession.stim == stim, 'istim'] = istim
mySession.loc[mySession.perc == stim, 'iperc'] = istim
mySession.loc[:, 'istim'] = mySession.loc[:, 'istim'].astype(int)
mySession.loc[:, 'iperc'] = mySession.loc[:, 'iperc'].astype(int)
rho = pd.DataFrame(index=np.arange(nTrials),
columns=np.sort(mySession.istim.drop_duplicates()))
rho.loc[0, :] = 1
W = pd.DataFrame(index=np.arange(tbf.shape[0]), columns=rho.columns)
W.loc[:, :] = 1
#%%
sns.regplot(x='stim',
y='isChoiceLeft',
data=mySession,
logistic=True,
ci=None,
y_jitter=0.01)
plt.show()
#%% INITIAL CONDITIONS
# mySession.loc[0,'waitingTime'] = np.random.choice(np.arange(tbf.shape[1]), 1, p=pnorm((tbf.T @ W).values[:,mySession.iperc[0]])).item()
#
# mySession.loc[0,'feedbackTime'] = truncExp(1.5, .5, 8)
#%%
# hf[ipair], ha[ipair] = plt.subplots(1, 3, figsize=(10, 3))
hf, ha = plt.subplots(1, 3)
# %%
import seaborn as sns
import pandas as pd
from matplotlib.pyplot import *
sns.set_theme()
tem = pd.read_csv("CSV_files/first/tempYearly.csv")
rai = pd.read_csv("CSV_files/first/rainYearly.csv")
tem["Rainfall"] = rai["Rainfall"]
sns.regplot(
x="Rainfall",
y="Temperature",
data=tem[(0.0 <= tem['Rainfall']) & (tem['Rainfall'] < 10.0) &
(0.0 <= tem['Temperature']) & (tem['Temperature'] < 50.0)])
show()
df_join['TMB-Foundation-Value'])[0], 3)) + "/" +
str(
round(
st.pearsonr(df_join['TMB-Total-Variants'],
df_join['TMB-Foundation-Value'])[0], 3)) + "/" +
str(round(r2_score(y, y_slr), 3)))
plt.savefig("Fig_4_TMB_HMH_Foundation_Variants_Score_ScatterPlot_main.png")
plt.close()
### caris vs Foundation
x1 = np.reshape(
df_join[df_join['Source'] == "Caris"]['TMB-Total-Variants'].values,
(-1, 1))
y1 = df_join[df_join['Source'] == "Caris"]['TMB-Foundation-Value'].values
y1_slr = fitData(x1, y1, "simple-lr")
sns.regplot(x=x1, y=y1, ci=None)
plt.title("TMB Score Comparison-Caris, S/P/R^2= " +
str(round(st.spearmanr(x1, y1)[0], 3)) + "/" + str(
round(
st.pearsonr(
df_join[df_join['Source'] == "Caris"]
['TMB-Total-Variants'].values, y1)[0], 3)) + "/" +
str(round(r2_score(y1, y1_slr), 3)))
plt.savefig("TMB_HMH_Variants_Foundation_Score_ScatterPlot_Caris.png")
plt.close()
x2 = np.reshape(
df_join[df_join['Source'] == "Foundation"]['TMB-Total-Variants'].values,
(-1, 1))
y2 = df_join[df_join['Source'] == "Foundation"]['TMB-Foundation-Value'].values
y2_slr = fitData(x2, y2, "simple-lr")