wesslen

---
name: "Ryan Wesslen"
title: "cfpb complaints/reticulate"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(reticulate); library(tidyverse)
```

wesslen

---
title: "LDA vs CTM Experiment"
author: "Ryan Wesslen"
date: "Aug 28, 2019"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo=TRUE, warning=FALSE, message=FALSE)
```

wesslen

import spacy
from spacy import displacy

path = "en_core_web_sm"

nlp = spacy.load(path)

path_folder = "/path/to/file/"

import pandas as pd

wesslen

# step 1: create 4 new columns in by_country (get freq stats)
# *Mean = donors_mean
# *Lower = donors_mean - 2*donors_stdev
# *Upper = donors_mean + 2*donors_stdev
# *Type = "Std Dev"
freq_df <- by_country %>%
  mutate(Lower = donors_mean - 2*donors_stdev,
         Upper = donors_mean + 2*donors_stdev,
         Mean = donors_mean) %>%
  select(-donors_mean, -donors_stdev) %>%

wesslen

# for more on keras/tf for R, see https://blogs.rstudio.com/tensorflow/

library(keras)

mnist <- dataset_mnist()
x_train <- mnist$train$x
y_train <- mnist$train$y
x_test <- mnist$test$x
y_test <- mnist$test$y

wesslen

import spacy
import textacy
import pandas as pd
# load flat file
df = pd.read_csv("data/vispapers.csv", engine = "python")
# texts + metadata
texts = {
    "text": df.Abstract,
    "Conference": df.Conference,
    "Year": df.Year

wesslen

import spacy
import numpy as np
import pandas as pd
import altair as alt
#alt.renderers.enable('default') # if in jupyter, need to activate

def cos_sim(t1, t2):
    return np.dot(t1.vector, t2.vector) / (t1.vector_norm * t2.vector_norm)

nlp = spacy.load("en_core_web_lg")

wesslen

import pandas as pd

df = pd.read_csv("vispapers.csv", engine = "python")

df.shape

# count keywords
df['AuthorKeywords'] = df['AuthorKeywords'].apply(str)

raw = [_.lower() for _ in df['AuthorKeywords'] if _ != 'nan']

wesslen

FROM python:3.7
EXPOSE 8501
WORKDIR /app
COPY requirements.txt ./requirements.txt
RUN pip3 install -r requirements.txt
COPY . .
CMD streamlit run app.py

wesslen

library(tidyverse)

returns <- read_csv("data/returns.csv") %>%
  select(Year, equities_sp, treasury_10yr) %>%
  gather(key = "Asset", value = "Returns", -Year) %>%
  mutate(Asset = ifelse(Asset=="equities_sp",
                        "Asset A: High risk, high return",
                        "Asset B: Low risk, low return"))

set.seed(123)