ChengzhiZhao

use plotters::prelude::*;
use std::error::Error;
use fast_float::parse;

fn read_csv() -> Result<(Vec<f64>,Vec<i32>), Box<dyn Error>> {
    // Build the CSV reader and iterate over each record.
    let mut rdr = csv::Reader::from_path("~/Downloads/kc_house_data.csv")?;
    let mut price:Vec<f64> = Vec::new();
    let mut sqft_living:Vec<i32> = Vec::new();

ChengzhiZhao

use plotters::prelude::*;
use std::error::Error;

fn read_csv() -> Result<(Vec<String>, Vec<f64>,Vec<f64>), Box<dyn Error>> {
    // Build the CSV reader and iterate over each record.
    // Data Source is from https://www.kaggle.com/johnharshith/hollywood-theatrical-market-synopsis-1995-to-2021/version/2?select=TopGenres.csv
    let mut rdr = csv::Reader::from_path("~/Downloads/TopGenres.csv")?;
    let mut genres:Vec<String> = Vec::new();
    let mut movies:Vec<f64> = Vec::new();
    let mut market_share:Vec<f64> = Vec::new();

ChengzhiZhao

import prefect
from prefect import task, Flow

@task
def hello_task():
    logger = prefect.context.get("logger")
    logger.info("Hello world!")

with Flow("hello-flow") as flow:
    hello_task()

ChengzhiZhao

df.withColumn("salt_random_column", (rand * n).cast(IntegerType)) // n is the size of partition you'd like to have
  .groupBy(groupByFields, "salt_random_column")
  .agg(aggFields)
  .groupBy(groupByFields)
  .agg(aggFields)

ChengzhiZhao

use arrow::util::pretty;
use std::time::{Duration, Instant};
use datafusion::datasource::csv::CsvReadOptions;
use datafusion::error::Result;
use datafusion::execution::context::ExecutionContext;

/// This example demonstrates executing a simple query against an Arrow data source (CSV) and
/// fetching results
fn main() -> Result<()> {
    let start = Instant::now();

ChengzhiZhao

use std::sync::Arc;

extern crate arrow;
extern crate datafusion;
use arrow::array::{Int32Array, Float64Array};
use arrow::datatypes::{DataType, Field, Schema};
use std::time::{Duration, Instant};
use datafusion::execution::context::ExecutionContext;

/// This example demonstrates executing a simple query against an Arrow data source (CSV) and

ChengzhiZhao

import pandas as pd
import plotly.express as px

# Parse Data
url="https://raw.githubusercontent.com/ChengzhiZhao/jupyter-notebooks/master/slickdeals_data_file.csv"
df=pd.read_csv(url,header=None,names=['datetime','store','title','item_url','deal_price','original_price', 'like', 'comments'])
df['datetime'] = pd.to_datetime(df['datetime'])

# Data Anlytics#
# Frequency

ChengzhiZhao

import scrapy
import csv
from datetime import datetime
from scrapy.selector import Selector


class SlickDealsSpider(scrapy.Spider):
    name = "slickdeals"

    def start_requests(self):

ChengzhiZhao

from airflow.models import DAG
from datetime import datetime, timedelta
from airflow.operators.bash_operator import BashOperator

args = {
    'owner': 'Airflow',
    'start_date': datetime(2020, 4, 1),
    'depends_on_past': True,
}

ChengzhiZhao

import dask
import dask.dataframe as dd
import time
from dask.distributed import Client, progress

client = Client(threads_per_worker=2, n_workers=2)
client

def call_api():
    time.sleep(1)