Navot's words counts_

Navot's words counts: 
vectorizer = CountVectorizer(vocabulary = kws)
X = vectorizer.fit_transform(corpus).toarray()

Precision recall curve: 
from sklearn.metrics import precision_recall_curve
p, r, thresholds = precision_recall_curve(y_test, lr_probs)
plt.plot(p,r)

parsing dates:
from dateutil.parser import parse
open_close_dates_df['Date/Time Opened'].apply(lambda d : parse(d) if isinstance(d, str) else d)

plotly - export graph to html: 
import plotly.express as px

import pandas as pd
df = pd.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/finance-charts-apple.csv')

fig = px.line(df, x='Date', y='AAPL.High')
fig.write_html("/Users/mmandelbrod/Documents/plotly_test.html")
fig.show()

#Connecting to a remote server using python, and executing commands there: 
client = paramiko.SSHClient()
client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
client.connect(hostname='<hostname>', username=<user_name>, password=<password>, look_for_keys=False)

#Executing on the server:
algorithm_current_params = algorithm_params.format(use_tags = use_tags, 
        tags_fn=tags_fn, 
        simple_bind=simple_bind, 
        before_reply_info=before_reply_info, 
        before_write_general=before_write_general, 
        before_change_summary=before_change_summary, 
        after_declare_work = after_declare_work, 
        before_next_write = before_next_write)
spark_submit_run_string = spark_submit_format.format(scriptPath=script_path, fromDate=from_date, toDate=to_date, account=account, algorithm_params=algorithm_current_params)

stdin, stdout, stderr = client.exec_command(
    spark_submit_run_string,
    timeout=9999999)
ssh_output = stdout.read().decode('UTF-8')
ssh_error = stderr.read().decode('UTF-8')

print('output: ' + ssh_output)
print('Error: ' + ssh_error)

#Extracting the file from hdfs to the server
stdin, stdout, stderr = client.exec_command(hadoop_get_merge_format.format(user_name=user_name,file_name=work_periods_file_name),
                                            timeout=9999999)
ssh_output = stdout.read().decode('UTF-8')
ssh_error = stderr.read().decode('UTF-8')

print('output: ' + ssh_output)
print('Error: ' + ssh_error)

#Downloading to local 
download_remote_file_path = '{file_name}.txt'.format(file_name=work_periods_file_name)
download_local_file_path = '{file_name}.txt'.format(file_name=work_periods_file_name)
ftp_client = client.open_sftp()
ftp_client.get(download_remote_file_path, download_local_file_path)
ftp_client.close()