读取文件并在Python中绘制CDF

Question

我需要以秒为单位读取带有时间戳的长文件，以及使用numpy或scipy的CDF图。我确实试过numpy，但似乎输出不是它应该是什么。以下代码：任何建议表示赞赏。

import numpy as np
import matplotlib.pyplot as plt

data = np.loadtxt('Filename.txt')
sorted_data = np.sort(data)
cumulative = np.cumsum(sorted_data)

plt.plot(cumulative)
plt.show()

Answer 1

您有两种选择：

1：您可以先将数据分区。使用numpy.histogram函数

可以轻松完成此操作

import numpy as np
import matplotlib.pyplot as plt

data = np.loadtxt('Filename.txt')

# Choose how many bins you want here
num_bins = 20

# Use the histogram function to bin the data
counts, bin_edges = np.histogram(data, bins=num_bins, normed=True)

# Now find the cdf
cdf = np.cumsum(counts)

# And finally plot the cdf
plt.plot(bin_edges[1:], cdf)

plt.show()

2：而不是使用numpy.cumsum，只需将sorted_data数组绘制为小于数组中每个元素的项目数（请参阅此答案以获取更多详细信息https://stackoverflow.com/a/11692365/588071）：< / p>

import numpy as np

import matplotlib.pyplot as plt

data = np.loadtxt('Filename.txt')

sorted_data = np.sort(data)

yvals=np.arange(len(sorted_data))/float(len(sorted_data)-1)

plt.plot(sorted_data,yvals)

plt.show()

Answer 2

为了完整起见，您还应该考虑：

• 重复：您可以在数据中多次使用相同的点。
• 点之间可以有不同的距离
• 积分可以浮动

您可以使用numpy.histogram，设置垃圾箱边缘，使每个垃圾箱只收集一个点的所有出现次数。 您应该保留density=False，因为根据文档：

  

请注意，除非选择单位宽度的区间，否则直方图值的总和不会等于1

您可以标准化每个bin中的元素数量除以数据的大小。

import numpy as np
import matplotlib.pyplot as plt

def cdf(data):

    data_size=len(data)

    # Set bins edges
    data_set=sorted(set(data))
    bins=np.append(data_set, data_set[-1]+1)

    # Use the histogram function to bin the data
    counts, bin_edges = np.histogram(data, bins=bins, density=False)

    counts=counts.astype(float)/data_size

    # Find the cdf
    cdf = np.cumsum(counts)

    # Plot the cdf
    plt.plot(bin_edges[0:-1], cdf,linestyle='--', marker="o", color='b')
    plt.ylim((0,1))
    plt.ylabel("CDF")
    plt.grid(True)

    plt.show()

例如，使用以下数据：

#[ 0.   0.   0.1  0.1  0.2  0.2  0.3  0.3  0.4  0.4  0.6  0.8  1.   1.2]
data = np.concatenate((np.arange(0,0.5,0.1),np.arange(0.6,1.4,0.2),np.arange(0,0.5,0.1)))
cdf(data)

你会得到：

您还可以插入cdf以获得连续函数（使用线性插值或三次样条曲线）：

import numpy as np
import matplotlib.pyplot as plt
from scipy.interpolate import interp1d

def cdf(data):

    data_size=len(data)

    # Set bins edges
    data_set=sorted(set(data))
    bins=np.append(data_set, data_set[-1]+1)

    # Use the histogram function to bin the data
    counts, bin_edges = np.histogram(data, bins=bins, density=False)

    counts=counts.astype(float)/data_size

    # Find the cdf
    cdf = np.cumsum(counts)

    x = bin_edges[0:-1]
    y = cdf

    f = interp1d(x, y)
    f2 = interp1d(x, y, kind='cubic')

    xnew = np.linspace(0, max(x), num=1000, endpoint=True)

    # Plot the cdf
    plt.plot(x, y, 'o', xnew, f(xnew), '-', xnew, f2(xnew), '--')
    plt.legend(['data', 'linear', 'cubic'], loc='best')
    plt.title("Interpolation")
    plt.ylim((0,1))
    plt.ylabel("CDF")
    plt.grid(True)

    plt.show()

Answer 3

快速回答，

plt.plot(sorted_data, np.linspace(0,1,sorted_data.size)

应该得到你想要的东西

Answer 4

以下是我实施的步骤：

1.分类您的数据

2.计算每个'x'

的累积概率

public function pay(){
        //Set variables for paypal form
        $returnURL = site_url(AGENT_ROLE.$this->data['controller']."/Success"); //payment success url
        $cancelURL = site_url(AGENT_ROLE.$this->data['controller']."/Cancelled");//payment cancel url
        $notifyURL = site_url(AGENT_ROLE.$this->data['controller']."/Notification"); //ipn url
        //get particular product data
        $product = "test product";
        $userID = 1; //current user id
        $logo = base_url().'assets/images/logo/logo.png';

        $this->paypal_lib->add_field('return', $returnURL);
        $this->paypal_lib->add_field('cancel_return', $cancelURL);
        $this->paypal_lib->add_field('notify_url', $notifyURL);
        $this->paypal_lib->add_field('item_name', $product);
        $this->paypal_lib->add_field('custom', $userID);
        $this->paypal_lib->add_field('item_number',  1);
        $this->paypal_lib->add_field('amount',  100.00);        
        $this->paypal_lib->image($logo);
        $this->paypal_lib->paypal_auto_form();
    }

    function success(){
        //get the transaction data
//        $paypalInfo = $this->input->get();
//        $paypalInfo2 = $this->input->post();
//        $data['item_number'] = $paypalInfo['item_number']; 
//        $data['txn_id'] = $paypalInfo["tx"];
//        $data['payment_amt'] = $paypalInfo["amt"];
//        $data['currency_code'] = $paypalInfo["cc"];
//        $data['status'] = $paypalInfo["st"];
//        $item_name = $_POST['item_name'];
//        $item_number = $_POST['item_number'];
//        $payment_status = $_POST['payment_status'];
//        $payment_amount = $_POST['mc_gross'];
//        $payment_currency = $_POST['mc_currency'];
//        $txn_id = $_POST['txn_id'];
//        $receiver_email = $_POST['receiver_email'];
//        $payer_email = $_POST['payer_email'];
        //pass the transaction data to view

        var_dump(fsockopen ('https://www.sandbox.paypal.com/', 443, $errno, $errstr, 30));
        var_dump($_POST);
     }

     function cancel(){
//        $this->load->view('paypal/cancel');
         echo "Cancelled";
     }

     function ipn(){
        //paypal return transaction details array
        $paypalInfo    = $this->input->post();

        $data['user_id'] = $paypalInfo['custom'];
        $data['product_id']    = $paypalInfo["item_number"];
        $data['txn_id']    = $paypalInfo["txn_id"];
        $data['payment_gross'] = $paypalInfo["mc_gross"];
        $data['currency_code'] = $paypalInfo["mc_currency"];
        $data['payer_email'] = $paypalInfo["payer_email"];
        $data['payment_status']    = $paypalInfo["payment_status"];

        $paypalURL = $this->paypal_lib->paypal_url;  
//        $paypalURL = 'https://www.sandbox.paypal.com/cgi-bin/webscr';          
        $result    = $this->paypal_lib->curlPost($paypalURL,$paypalInfo);

        //check whether the payment is verified
        if(preg_match("/VERIFIED/i",$result)){
            //insert the transaction data into the database
//            $this->product->insertTransaction($data);
            var_dump("IPN SUCCESS");
        }
    }

示例：

import numpy as np
import matplotlib.pyplab as plt

def cdf(data):
    n = len(data)
    x = np.sort(data) # sort your data
    y = np.arange(1, n + 1) / n # calculate cumulative probability
    return x, y

x_data, y_data = cdf(your_data)
plt.plot(x_data, y_data) 

图： The link of graph

Answer 5

如果存在许多重复值（这是因为我们只需要对唯一值进行排序），这里的实现效率会更高一些。它将CDF绘制为阶梯函数，严格来说就是这样。

import sys

import numpy as np
import matplotlib.pyplot as plt

from collections import Counter


def read_data(fp):
    t = []
    for line in fp:
        x = float(line.rstrip())
        t.append(x)
    return t


def main(script, filename=None):
    if filename is None:
        fp = sys.stdin
    else:
        fp = open(filename)

    t = read_data(fp)
    counter = Counter(t)

    xs = counter.keys()
    xs.sort()

    ys = np.cumsum(counter.values()).astype(float)
    ys /= ys[-1]

    options = dict(linewidth=3, alpha=0.5)
    plt.step(xs, ys, where='post', **options)
    plt.xlabel('Values')
    plt.ylabel('CDF')
    plt.show()


if __name__ == '__main__':
    main(*sys.argv)

Answer 6

如果要使用Seaborn库，请按照以下步骤操作：

import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt
data = pd.read_csv('Filename.txt', sep=" ", header=None)
plt.figure()
sns.kdeplot(data,cumulative=True)
plt.show()