-Southern Brave:- Historial positivo contra equipos escoceses.
- Capacidad ofensiva destacada gracias a bateadores experimentados.
- Probabilidad alta de tomar ventaja temprana si logran romper bienvenida defensa contraria.
- Nuevas incorporaciones como Imad Wasim pueden cambiar dinámicas tradicionales.
Nuestra recomendación basada en análisis:
Dada esta información detallada,<|end_of_generation|><|repo_name|>pepetools/pepetools<|file_sep|>/pepetools/utils.py
import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.axes_grid1 import make_axes_locatable
import scipy.stats as stats
import pandas as pd
from pandas import DataFrame
from collections import OrderedDict
from itertools import cycle
import seaborn as sns
import math
def linear_reg(x,y):
"""Returns the slope and intercept of the linear regression between x and
y.
"""
slope = np.polyfit(x,y,1)[0]
intercept = np.polyfit(x,y,1)[1]
return slope , intercept
def plot_with_linear_regression(x,y,title=None,slope=None):
"""Plots x and y and their linear regression if slope is not None.
"""
if slope is None:
slope , intercept = linear_reg(x,y)
else:
intercept = np.mean(y) - slope*np.mean(x)
plt.plot(x,y,'ko',label='Data')
plt.plot(x,slope*x + intercept,'r-',label='Linear regression')
plt.xlabel('X')
plt.ylabel('Y')
if title is not None:
plt.title(title)
plt.legend()
plt.show()
def normalize(data):
data_norm = data - np.mean(data)
data_norm /= np.std(data_norm)
return data_norm
def get_significant_indices_from_bonferroni_corrected_pvalues(p_values,alpha):
p_values_corrected = [p*len(p_values) for p in p_values]
significant_indices = [i for i,p in enumerate(p_values_corrected) if p<=alpha]
return significant_indices
def get_significant_indices_from_fdr_corrected_pvalues(p_values,alpha):
p_values_corrected = stats.multipletests(p_values,alpha=alpha)[1]
significant_indices = [i for i,p in enumerate(p_values_corrected) if p<=alpha]
return significant_indices
def calculate_confidence_interval(mean,std,n,alpha=0.05):
numpy.random.seed(42)
mean = float(mean)
std = float(std)
n = float(n)
t_multiplier = stats.t.ppf(1-alpha/2,n-1)
confidence_interval = t_multiplier * std/math.sqrt(n)
return confidence_interval
def plot_confidence_intervals(data,title=None):
mean_data = np.mean(data,axis=1)
std_data = np.std(data,axis=1)
n_data = len(data[0])
confidence_interval_data = calculate_confidence_interval(mean_data,std_data,n_data)
errorbar_plot([mean_data - confidence_interval_data],yerr=[confidence_interval_data],title=title)
def errorbar_plot(data,yerr=None,xerr=None,title=None,label=None,color='k'):
if title is not None:
plt.title(title)
if label is not None:
plt.errorbar(range(len(data)),data,yerr=yerr,xerr=xerr,color=color,label=label)
else:
plt.errorbar(range(len(data)),data,yerr=yerr,xerr=xerr,color=color)
plt.xlabel('Data points')
plt.ylabel('Data values')
def plot_mean_and_std(data,title=None):
mean_data = np.mean(data,axis=1)
std_data = np.std(data,axis=1)
errorbar_plot(mean_data,yerr=std_data,title=title)
def plot_mean_and_confidence_interval(data,title=None):
mean_data = np.mean(data,axis=1)
std_data = np.std(data,axis=1)
n_data = len(data[0])
confidence_interval_data = calculate_confidence_interval(mean_data,std_data,n_data)
errorbar_plot(mean_data,yerr=confidence_interval_data,title=title)
def plot_boxplots(data_dict,title=None):
if title is not None:
plt.title(title)
df_dict_ordered = OrderedDict(sorted(data_dict.items(), key=lambda t: t[0]))
df_dict_ordered_df=pd.DataFrame.from_dict(df_dict_ordered).T.reset_index().T
df_dict_ordered_df.columns=['Variable','Value']
sns.boxplot(x='Variable',y='Value',data=df_dict_ordered_df)
def plot_barplots_with_errorbars(data_dict,title=None,label=None):
if title is not None:
plt.title(title)
means=[]
errors=[]
for k,v in data_dict.items():
mean=np.mean(v,axis=0)
std=np.std(v,axis=0)/np.sqrt(len(v))
means.append(mean[0])
errors.append(std[0])
width=0.8
xpos
