| \n", + " | timestamp | \n", + "cpi | \n", + "fed | \n", + "spy | \n", + "gld | \n", + "
|---|---|---|---|---|---|
| 0 | \n", + "2024-05-01 | \n", + "314.069 | \n", + "5.33 | \n", + "525.6718 | \n", + "215.30 | \n", + "
| 1 | \n", + "2024-04-01 | \n", + "313.548 | \n", + "5.33 | \n", + "500.3636 | \n", + "211.87 | \n", + "
| 2 | \n", + "2024-03-01 | \n", + "312.332 | \n", + "5.33 | \n", + "521.3857 | \n", + "205.72 | \n", + "
| 3 | \n", + "2024-02-01 | \n", + "310.326 | \n", + "5.33 | \n", + "504.8645 | \n", + "189.31 | \n", + "
| 4 | \n", + "2024-01-01 | \n", + "308.417 | \n", + "5.33 | \n", + "479.8240 | \n", + "188.45 | \n", + "
| \n", + " | cpi | \n", + "fed | \n", + "spy | \n", + "gld | \n", + "
|---|---|---|---|---|
| count | \n", + "234.000000 | \n", + "234.000000 | \n", + "234.000000 | \n", + "234.000000 | \n", + "
| mean | \n", + "239.904709 | \n", + "1.588761 | \n", + "199.248881 | \n", + "124.362344 | \n", + "
| std | \n", + "30.299220 | \n", + "1.879657 | \n", + "122.947398 | \n", + "40.170234 | \n", + "
| min | \n", + "190.300000 | \n", + "0.050000 | \n", + "55.148800 | \n", + "41.650000 | \n", + "
| 25% | \n", + "216.963500 | \n", + "0.120000 | \n", + "98.790475 | \n", + "101.575000 | \n", + "
| 50% | \n", + "236.409000 | \n", + "0.390000 | \n", + "164.878300 | \n", + "123.360000 | \n", + "
| 75% | \n", + "256.327500 | \n", + "2.480000 | \n", + "270.226075 | \n", + "159.787500 | \n", + "
| max | \n", + "314.069000 | \n", + "5.330000 | \n", + "525.671800 | \n", + "215.300000 | \n", + "
| \n", + " | timestamp | \n", + "cpi | \n", + "fed | \n", + "spy | \n", + "gld | \n", + "
|---|---|---|---|---|---|
| 0 | \n", + "2024-05-01 | \n", + "314.069 | \n", + "5.33 | \n", + "525.6718 | \n", + "215.30 | \n", + "
| 1 | \n", + "2024-04-01 | \n", + "313.548 | \n", + "5.33 | \n", + "500.3636 | \n", + "211.87 | \n", + "
| 2 | \n", + "2024-03-01 | \n", + "312.332 | \n", + "5.33 | \n", + "521.3857 | \n", + "205.72 | \n", + "
| 3 | \n", + "2024-02-01 | \n", + "310.326 | \n", + "5.33 | \n", + "504.8645 | \n", + "189.31 | \n", + "
| 4 | \n", + "2024-01-01 | \n", + "308.417 | \n", + "5.33 | \n", + "479.8240 | \n", + "188.45 | \n", + "
![](\"https://www.investopedia.com/thmb/Xz1Mnf7Ji54AAfAT1fsiwcZvmxM=/750x0/filters:no_upscale():max_bytes(150000):strip_icc():format(webp)/correlation_defintion_-9d2d662781724d61af6d6322a2a294b5.jpg\")
\n",
+ "\n",
+ "\n",
+ "> Investment managers, traders, and analysts find it very important to calculate correlation because the risk reduction benefits of diversification rely on this statistic."
+ ],
+ "metadata": {
+ "id": "W_K7rK_TVDHr"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Let's take a quick detour to make a scaled version of this data, to make it easier to plot all these different series on a graph, so we can perhaps start to get a sense of how their movements might correlate (in an unofficial way)."
+ ],
+ "metadata": {
+ "id": "4AxAx5WzSojE"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "scaled_df = df.copy()\n",
+ "scaled_df.index = df[\"timestamp\"] # save the ts for charting, knowing we will remove it\n",
+ "scaled_df.drop(columns=[\"timestamp\"], inplace=True) # remove the ts column, in preparation to operate on all numeric columns\n",
+ "scaled_df = scaled_df / scaled_df.max() # dividing all numeric col values by their column's max. there are many alternative methods for scaling the data\n",
+ "scaled_df.head()\n",
+ "\n",
+ "import plotly.express as px\n",
+ "px.line(scaled_df, y=[\"cpi\", \"fed\", \"spy\", \"gld\",\n",
+ " #\"btc\"\n",
+ " ],\n",
+ " title=\"Scaled data over time\")"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 542
+ },
+ "id": "jYW5YzrbRDks",
+ "outputId": "0a055557-f6c0-4161-fd91-1951281df652"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/html": [
+ "\n",
+ "\n",
+ "\n",
+ " | \n", + " | cpi | \n", + "fed | \n", + "spy | \n", + "gld | \n", + "
|---|---|---|---|---|
| cpi | \n", + "1.000000 | \n", + "0.078102 | \n", + "0.949065 | \n", + "0.823717 | \n", + "
| fed | \n", + "0.078102 | \n", + "1.000000 | \n", + "0.172821 | \n", + "-0.263213 | \n", + "
| spy | \n", + "0.949065 | \n", + "0.172821 | \n", + "1.000000 | \n", + "0.719160 | \n", + "
| gld | \n", + "0.823717 | \n", + "-0.263213 | \n", + "0.719160 | \n", + "1.000000 | \n", + "
| \n", + " | cpi | \n", + "fed | \n", + "spy | \n", + "gld | \n", + "
|---|---|---|---|---|
| cpi | \n", + "1.000000 | \n", + "-0.102732 | \n", + "0.953588 | \n", + "0.790661 | \n", + "
| fed | \n", + "-0.102732 | \n", + "1.000000 | \n", + "0.005936 | \n", + "-0.308626 | \n", + "
| spy | \n", + "0.953588 | \n", + "0.005936 | \n", + "1.000000 | \n", + "0.714306 | \n", + "
| gld | \n", + "0.790661 | \n", + "-0.308626 | \n", + "0.714306 | \n", + "1.000000 | \n", + "
:max_bytes(150000):strip_icc():format(webp)/correlation_defintion_-9d2d662781724d61af6d6322a2a294b5.jpg)
+
+
+> Investment managers, traders, and analysts find it very important to calculate correlation because the risk reduction benefits of diversification rely on this statistic.
+
+Let's take a quick detour to make a scaled version of this data, to make it easier to plot all these different series on a graph, so we can perhaps start to get a sense of how their movements might correlate (in an unofficial way).
+"""
+
+scaled_df = df.copy()
+scaled_df.index = df["timestamp"] # save the ts for charting, knowing we will remove it
+scaled_df.drop(columns=["timestamp"], inplace=True) # remove the ts column, in preparation to operate on all numeric columns
+scaled_df = scaled_df / scaled_df.max() # dividing all numeric col values by their column's max. there are many alternative methods for scaling the data
+scaled_df.head()
+
+import plotly.express as px
+px.line(scaled_df, y=["cpi", "fed", "spy", "gld",
+ #"btc"
+ ],
+ title="Scaled data over time")
+
+"""Looks like the [...] has been moving [upward/downward] at a time when [...] has been moving [upward/downward]. We might start to suspect they are correlated in a [pos/neg] way.
+
+> NOTE: correlation does not imply causation!
+
+Let's now perform tests for correlation in more official / formal ways.
+
+## Correlation Considerations
+
+Certain methods for calculating correlation may depend on the normality of our data's distribution, or the sample size, so we should keep these in mind as we determine if we are able to calculate correlation, and which method to use.
+
+https://www.investopedia.com/terms/n/nonparametric-method.asp
+
+
+> The nonparametric method refers to a type of statistic that does not make any assumptions about the characteristics of the sample (its parameters) or whether the observed data is quantitative or qualitative.
+>
+> Nonparametric statistics can include certain descriptive statistics, statistical models, inference, and statistical tests. The model structure of nonparametric methods is not specified a priori but is instead determined from data.
+>
+> Common nonparametric tests include Chi-Square, Wilcoxon rank-sum test, Kruskal-Wallis test, and Spearman's rank-order correlation.
+>
+> In contrast, well-known statistical methods such as ANOVA, Pearson's correlation, t-test, and others do make assumptions about the data being analyzed. One of the most common parametric assumptions is that population data have a "normal distribution."
+
+## Correlation with `scipy`
+
+We can always calculate correlation between two lists of numbers, using the `pearsonr` and `spearmanr` functions from the `scipy` package.
+
+One difference between these two correlation methods is that Spearman is more robust to (i.e. less affected by) outliers. Also being nonparametric, the Spearman method does not assume our data is normally distributed.
+
+https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.pearsonr.html
+
+> Pearson correlation coefficient and p-value for testing non-correlation.
+>
+> The Pearson correlation coefficient [1] measures the linear relationship between two datasets. Like other correlation coefficients, this one varies between -1 and +1 with 0 implying no correlation. Correlations of -1 or +1 imply an exact linear relationship. Positive correlations imply that as x increases, so does y. Negative correlations imply that as x increases, y decreases.
+>
+> This function also performs a test of the null hypothesis that the distributions underlying the samples are uncorrelated and normally distributed. (See Kowalski [3] for a discussion of the effects of non-normality of the input on the distribution of the correlation coefficient.) The p-value roughly indicates the probability of an uncorrelated system producing datasets that have a Pearson correlation at least as extreme as the one computed from these datasets.
+
+https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.spearmanr.html
+
+> Calculate a Spearman correlation coefficient with associated p-value.
+>
+> The Spearman rank-order correlation coefficient is a nonparametric measure of the monotonicity of the relationship between two datasets. Like other correlation coefficients, this one varies between -1 and +1 with 0 implying no correlation. Correlations of -1 or +1 imply an exact monotonic relationship. Positive correlations imply that as x increases, so does y. Negative correlations imply that as x increases, y decreases.
+>
+> The p-value roughly indicates the probability of an uncorrelated system producing datasets that have a Spearman correlation at least as extreme as the one computed from these datasets. Although calculation of the p-value does not make strong assumptions about the distributions underlying the samples, it is only accurate for very large samples (>500 observations). For smaller sample sizes, consider a permutation test instead (see docs for examples).
+"""
+
+from scipy.stats import pearsonr
+
+x = df["fed"]
+y = df["spy"]
+
+result = pearsonr(x, y)
+print(result)
+
+from scipy.stats import spearmanr
+
+x = df["fed"]
+y = df["spy"]
+
+result = spearmanr(x, y)
+print(result)
+
+"""## Correlation Matrix with `pandas`
+
+OK sure we can calculate correlation between two sets of data. But what if we wanted to calculate correlation between many different data sets? We could perhaps set up a loop, but there is an easier way.
+
+If we have a pandas dataframe, we can use it's `corr()` method to produce a "correlation matrix", which shows us the "pairwise correlation of columns", in other words, the correlation of each column with respect to each other column.
+
+https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.corr.html
+"""
+
+#df.corr(method="pearson") # method is pearson by default
+df.corr(method="pearson", numeric_only=True) # numeric_only to suppress warning
+
+#df.corr(method="spearman")
+df.corr(method="spearman", numeric_only=True) # numeric_only to suppress warning
+
+"""We may begin to notice the diagonal of 1s values. This is because each dataset is perfectly positively correlated with itself.
+
+We may also start to notice the symmetry of values mirrored across the diagonal. In other words, the value in column 1, row 4 is the same as the value in column 4, row 1.
+
+## Plotting Correlation Matrix
+
+It may not be easy to quickly interpret the rest of the values in the correlation matrix, but if we plot it with colors as a "heat map" then we will be able to use color to more easily interpret the data and tell a story.
+
+### Correlation Heatmap with `plotly`
+
+https://plotly.com/python-api-reference/generated/plotly.express.imshow.html
+"""
+
+# https://plotly.com/python/heatmaps/
+# https://plotly.com/python-api-reference/generated/plotly.express.imshow.html
+import plotly.express as px
+
+cor_mat = df.corr(method="spearman", numeric_only=True) # using numeric_only to suppress warning
+
+title= "Spearman Correlation between Economic Indicators"
+fig = px.imshow(cor_mat,
+ height=600, # title=title,
+ text_auto= ".2f", # round to two decimal places
+ color_continuous_scale="Blues",
+ color_continuous_midpoint=0, # set color midpoint at zero because correlation coeficient ranges from -1 to 1 (see correlation notes)
+ labels={"x": "Indicator", "y": "Indicator"}
+)
+fig.update_layout(title={'text': title, 'x':0.485, 'xanchor': 'center'}) # https://stackoverflow.com/questions/64571789/center-plotly-title-by-default
+fig.show()
+
+"""What stories can we tell with the correlation heatmap? Which indicators are most positively correlated? Which are most negatively correlated?
+
+Is gold a hedge against inflation, or is there another indicator which may be a better hedge?
+
+"""
\ No newline at end of file
diff --git a/docs/notes/applied-stats/overview.qmd b/docs/notes/applied-stats/overview.qmd
new file mode 100644
index 0000000..545f655
--- /dev/null
+++ b/docs/notes/applied-stats/overview.qmd
@@ -0,0 +1,5 @@
+# Applied Statistics
+
+
+ + [Statistical Tests](./Basic_Statistics_Overview.ipynb)
+ + [Correlation](Correlation.ipynb)
diff --git a/docs/notes/fetching-data/apis.qmd b/docs/notes/fetching-data/apis.qmd
index 59b8f89..0d79d98 100644
--- a/docs/notes/fetching-data/apis.qmd
+++ b/docs/notes/fetching-data/apis.qmd
@@ -1 +1,11 @@
+---
+format:
+ html:
+ code-fold: false
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+
# APIs
diff --git a/docs/notes/fetching-data/csv-data.qmd b/docs/notes/fetching-data/csv-data.qmd
index 96e0c35..e02348a 100644
--- a/docs/notes/fetching-data/csv-data.qmd
+++ b/docs/notes/fetching-data/csv-data.qmd
@@ -1,3 +1,13 @@
+---
+format:
+ html:
+ code-fold: false
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+
# Fetching CSV Data
diff --git a/docs/notes/fetching-data/html-web-scraping.qmd b/docs/notes/fetching-data/html-web-scraping.qmd
index d911bbe..8dab422 100644
--- a/docs/notes/fetching-data/html-web-scraping.qmd
+++ b/docs/notes/fetching-data/html-web-scraping.qmd
@@ -1,3 +1,13 @@
+---
+format:
+ html:
+ code-fold: false
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+
# Fetching HTML Data
If the data you want to fetch is in XML or HTML format, we can use the `requests` package to fetch it, and the `beautifulsoup4` package to process it.
diff --git a/docs/notes/fetching-data/json-data.qmd b/docs/notes/fetching-data/json-data.qmd
index e0208e5..fb7b19c 100644
--- a/docs/notes/fetching-data/json-data.qmd
+++ b/docs/notes/fetching-data/json-data.qmd
@@ -1,3 +1,13 @@
+---
+format:
+ html:
+ code-fold: false
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+
# Fetching JSON Data
If the data you want to fetch is in JSON format, we can use the [`requests` package](https://requests.readthedocs.io/en/latest/) to fetch and process it.
diff --git a/docs/notes/pandas/dataframes.qmd b/docs/notes/pandas/dataframes.qmd
index 5e80d02..0d7d787 100644
--- a/docs/notes/pandas/dataframes.qmd
+++ b/docs/notes/pandas/dataframes.qmd
@@ -1 +1,11 @@
+---
+format:
+ html:
+ code-fold: false
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+
# Dataframes
diff --git a/docs/notes/pandas/grouping-pivoting.qmd b/docs/notes/pandas/grouping-pivoting.qmd
new file mode 100644
index 0000000..abe5308
--- /dev/null
+++ b/docs/notes/pandas/grouping-pivoting.qmd
@@ -0,0 +1,176 @@
+---
+format:
+ html:
+ code-fold: false #show
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+
+
+# Grouping and Pivoting
+
+In this sales dataset, you will see we have a row per date per product sold on that date.
+
+```{python}
+from pandas import read_csv, to_datetime
+
+sales_df = read_csv(f"https://raw.githubusercontent.com/prof-rossetti/python-for-finance/main/docs/data/monthly-sales.csv")
+sales_df["date"] = to_datetime(sales_df["date"])
+sales_df.head()
+```
+
+```{python}
+len(sales_df)
+```
+
+```{python}
+products = sales_df["product"].unique()
+print(products)
+```
+
+```{python}
+days = sales_df["date"].unique()
+print(len(days))
+print(days.min().date(), "...", days.max().date())
+```
+
+We know we can calculate total sales using a `Series` aggregation:
+
+
+```{python}
+sales_df["sales price"].sum().round(2)
+```
+
+But how can we calculate the total sales for each product?
+
+## Grouping
+
+Enter the [`groupby` method](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.groupby.html) for group-based aggregations.
+
+Calculating total sales per product, to identify the top selling products:
+
+```{python}
+sales_by_product = sales_df.groupby("product")["sales price"].sum()
+sales_by_product.sort_values(ascending=False)
+```
+
+Calculating total sales per day:
+
+```{python}
+sales_by_date = sales_df.groupby("date")["sales price"].sum()
+sales_by_date.sort_values(ascending=False).head()
+```
+
+Calculating total sales per day of week:
+
+
+```{python}
+sales_df["weekday"] = sales_df["date"].dt.strftime("%A")
+
+sales_by_weekday = sales_df.groupby("weekday")["sales price"].sum()
+sales_by_weekday.sort_values(ascending=False)
+```
+
+## Pivot Tables
+
+We can alternatively use the [`pivot_table` function](https://pandas.pydata.org/docs/reference/api/pandas.pivot_table.html) to perform more fine-grained grouping and aggregation.
+
+Parameters of the `pivot_table` function:
+
+ + The `index` parameter specifies the rows we want to wind up with (i.e. "row per what?").
+ + The `values` parameter specifies what columns we would like to aggregate.
+ + The `aggfunc` parameter specifies how to aggregate those columns. We can pass our own aggregation function(s) or get them from the `numpy` package. We can aggregate different columns differently.
+
+Pivoting by date:
+
+```{python}
+from pandas import pivot_table
+#import numpy as np
+
+dates_pivot = pivot_table(sales_df,
+ index=["date"],
+ values=["sales price", "units sold"],
+ aggfunc={
+ "sales price": "sum", #np.sum,
+ "units sold": "sum", #np.sum,
+ } # designate the agg function to be used for each original column. can use our own custom functions here as well
+)
+
+dates_pivot.rename(columns={"sales price": "sales_total", "units sold": "units_sold"}, inplace=True)
+dates_pivot.sort_values(by=["sales_total"], ascending=False, inplace=True)
+dates_pivot.head()
+```
+
+Pivoting by product:
+
+```{python}
+products_pivot = pivot_table(sales_df,
+ index=["product"],
+ values=["sales price", "units sold"],
+ aggfunc={
+ "sales price": "sum", #np.sum,
+ "units sold": "sum", #np.sum,
+ }
+)
+
+products_pivot.rename(columns={"sales price": "sales_total", "units sold": "units_sold"}, inplace=True)
+products_pivot.sort_values(by=["sales_total"], ascending=False, inplace=True)
+products_pivot.head()
+```
+
+Pivot by weekday:
+
+```{python}
+weekdays_pivot = pivot_table(sales_df,
+ index=["weekday"],
+ values=["sales price", "units sold"],
+ aggfunc={
+ "sales price": ["sum", "mean"], #np.mean,
+ #"units sold": ["sum", "mean"] #np.mean
+ }
+)
+
+weekdays_pivot.columns = ["sales_avg", "sales_total"]
+weekdays_pivot.sort_values(by=["sales_avg"], ascending=False, inplace=True)
+weekdays_pivot
+```
+
+These pivot tables are now suitable for charting as well:
+
+
+
+```{python}
+import plotly.express as px
+
+chart_df = dates_pivot.copy()
+#chart_df["date"] = chart_df.index
+chart_df.sort_values(by=["sales_total"], ascending=True, inplace=True)
+
+px.bar(chart_df, #x="date",
+ y="sales_total",
+ title="Sales by Day (March 2024)", height=350
+)
+```
+
+```{python}
+chart_df = products_pivot.copy()
+chart_df["product"] = chart_df.index
+chart_df.sort_values(by=["sales_total"], ascending=True, inplace=True)
+
+px.bar(chart_df, y="product", x="sales_total", orientation="h",
+ title="Top Selling Products (March 2024)", height=350
+)
+```
+
+
+```{python}
+chart_df = weekdays_pivot.copy()
+chart_df["weekday"] = chart_df.index
+chart_df.sort_values(by=["sales_avg"], ascending=True, inplace=True)
+
+px.bar(chart_df, y="weekday", x="sales_avg", orientation="h",
+ title="Average Sales per Weekday (March 2024)", height=350
+)
+```
diff --git a/docs/notes/pandas/joining-merging-simple.qmd b/docs/notes/pandas/joining-merging-simple.qmd
new file mode 100644
index 0000000..bb7efc0
--- /dev/null
+++ b/docs/notes/pandas/joining-merging-simple.qmd
@@ -0,0 +1,20 @@
+---
+format:
+ html:
+ code-fold: false #show
+jupyter: python3
+execute:
+ cache: true # re-render only when source changes
+---
+
+# Joining and Merging
+
+
+
+
+
+```{python}
+#from pandas import read_csv, to_datetime
+
+
+```
diff --git a/docs/notes/pandas/joining-merging.ipynb b/docs/notes/pandas/joining-merging.ipynb
new file mode 100644
index 0000000..00970ea
--- /dev/null
+++ b/docs/notes/pandas/joining-merging.ipynb
@@ -0,0 +1,5427 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Joining and Merging"
+ ],
+ "metadata": {
+ "id": "UwoohLt-OOEZ"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "To provide a practical example of merging data.\n",
+ "\n",
+ "Let's grab lots of different economic and market indicators from the AlphaVantage API, and prepare each source dataset in such a way that allows it to be merged with the others later."
+ ],
+ "metadata": {
+ "id": "nVSEPFOG5dBV"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "## Fetching Data"
+ ],
+ "metadata": {
+ "id": "-1qhOMoizxGl"
+ }
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "We have obtained an [AlphaVantage API Key](https://www.alphavantage.co/support/#api-key) and set it as a notebook secret."
+ ],
+ "metadata": {
+ "id": "kLQRHrmE5cln"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from google.colab import userdata\n",
+ "\n",
+ "API_KEY = userdata.get(\"ALPHAVANTAGE_API_KEY\")"
+ ],
+ "metadata": {
+ "id": "qGRE6QNZzSg3"
+ },
+ "execution_count": 111,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "### Inflation\n",
+ "\n",
+ "https://www.alphavantage.co/documentation/#inflation"
+ ],
+ "metadata": {
+ "id": "qH4Sth_0znlj"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "from pandas import read_csv\n",
+ "\n",
+ "request_url = f\"https://www.alphavantage.co/query?function=INFLATION&apikey={API_KEY}&datatype=csv\"\n",
+ "inflation = read_csv(request_url)\n",
+ "inflation.head()"
+ ],
+ "metadata": {
+ "id": "m_DQ2NxJzP9J",
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 206
+ },
+ "outputId": "06fd7d4f-8265-4696-ed3d-0414a5373660"
+ },
+ "execution_count": 112,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ " timestamp value\n",
+ "0 2022-01-01 8.002800\n",
+ "1 2021-01-01 4.697859\n",
+ "2 2020-01-01 1.233584\n",
+ "3 2019-01-01 1.812210\n",
+ "4 2018-01-01 2.442583"
+ ],
+ "text/html": [
+ "\n",
+ " | \n", + " | timestamp | \n", + "value | \n", + "
|---|---|---|
| 0 | \n", + "2022-01-01 | \n", + "8.002800 | \n", + "
| 1 | \n", + "2021-01-01 | \n", + "4.697859 | \n", + "
| 2 | \n", + "2020-01-01 | \n", + "1.233584 | \n", + "
| 3 | \n", + "2019-01-01 | \n", + "1.812210 | \n", + "
| 4 | \n", + "2018-01-01 | \n", + "2.442583 | \n", + "
| \n", + " | timestamp | \n", + "cpi | \n", + "
|---|---|---|
| 0 | \n", + "2024-05-01 | \n", + "314.069 | \n", + "
| 1 | \n", + "2024-04-01 | \n", + "313.548 | \n", + "
| 2 | \n", + "2024-03-01 | \n", + "312.332 | \n", + "
| 3 | \n", + "2024-02-01 | \n", + "310.326 | \n", + "
| 4 | \n", + "2024-01-01 | \n", + "308.417 | \n", + "
| \n", + " | timestamp | \n", + "fed | \n", + "
|---|---|---|
| 0 | \n", + "2024-05-01 | \n", + "5.33 | \n", + "
| 1 | \n", + "2024-04-01 | \n", + "5.33 | \n", + "
| 2 | \n", + "2024-03-01 | \n", + "5.33 | \n", + "
| 3 | \n", + "2024-02-01 | \n", + "5.33 | \n", + "
| 4 | \n", + "2024-01-01 | \n", + "5.33 | \n", + "
| \n", + " | timestamp | \n", + "spy | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-27 | \n", + "546.3700 | \n", + "
| 1 | \n", + "2024-05-31 | \n", + "525.6718 | \n", + "
| 2 | \n", + "2024-04-30 | \n", + "500.3636 | \n", + "
| 3 | \n", + "2024-03-28 | \n", + "521.3857 | \n", + "
| 4 | \n", + "2024-02-29 | \n", + "504.8645 | \n", + "
| \n", + " | timestamp | \n", + "spy | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-01 | \n", + "546.3700 | \n", + "
| 1 | \n", + "2024-05-01 | \n", + "525.6718 | \n", + "
| 2 | \n", + "2024-04-01 | \n", + "500.3636 | \n", + "
| 3 | \n", + "2024-03-01 | \n", + "521.3857 | \n", + "
| 4 | \n", + "2024-02-01 | \n", + "504.8645 | \n", + "
| \n", + " | timestamp | \n", + "spy | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-01 | \n", + "546.3700 | \n", + "
| 1 | \n", + "2024-05-01 | \n", + "525.6718 | \n", + "
| 2 | \n", + "2024-04-01 | \n", + "500.3636 | \n", + "
| 3 | \n", + "2024-03-01 | \n", + "521.3857 | \n", + "
| 4 | \n", + "2024-02-01 | \n", + "504.8645 | \n", + "
| \n", + " | timestamp | \n", + "gld | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-27 | \n", + "214.99 | \n", + "
| 1 | \n", + "2024-05-31 | \n", + "215.30 | \n", + "
| 2 | \n", + "2024-04-30 | \n", + "211.87 | \n", + "
| 3 | \n", + "2024-03-28 | \n", + "205.72 | \n", + "
| 4 | \n", + "2024-02-29 | \n", + "189.31 | \n", + "
| \n", + " | timestamp | \n", + "gld | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-01 | \n", + "214.99 | \n", + "
| 1 | \n", + "2024-05-01 | \n", + "215.30 | \n", + "
| 2 | \n", + "2024-04-01 | \n", + "211.87 | \n", + "
| 3 | \n", + "2024-03-01 | \n", + "205.72 | \n", + "
| 4 | \n", + "2024-02-01 | \n", + "189.31 | \n", + "
| \n", + " | timestamp | \n", + "btc | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-28 | \n", + "61499.77 | \n", + "
| 1 | \n", + "2024-05-31 | \n", + "67472.41 | \n", + "
| 2 | \n", + "2024-04-30 | \n", + "60622.10 | \n", + "
| 3 | \n", + "2024-03-31 | \n", + "71291.28 | \n", + "
| 4 | \n", + "2024-02-29 | \n", + "61179.03 | \n", + "
| \n", + " | timestamp | \n", + "btc | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-01 | \n", + "61499.77 | \n", + "
| 1 | \n", + "2024-05-01 | \n", + "67472.41 | \n", + "
| 2 | \n", + "2024-04-01 | \n", + "60622.10 | \n", + "
| 3 | \n", + "2024-03-01 | \n", + "71291.28 | \n", + "
| 4 | \n", + "2024-02-01 | \n", + "61179.03 | \n", + "
| \n", + " | timestamp | \n", + "cpi | \n", + "
|---|---|---|
| 0 | \n", + "2024-05-01 | \n", + "314.069 | \n", + "
| 1 | \n", + "2024-04-01 | \n", + "313.548 | \n", + "
| 2 | \n", + "2024-03-01 | \n", + "312.332 | \n", + "
| 3 | \n", + "2024-02-01 | \n", + "310.326 | \n", + "
| 4 | \n", + "2024-01-01 | \n", + "308.417 | \n", + "
| \n", + " | timestamp | \n", + "fed | \n", + "
|---|---|---|
| 0 | \n", + "2024-05-01 | \n", + "5.33 | \n", + "
| 1 | \n", + "2024-04-01 | \n", + "5.33 | \n", + "
| 2 | \n", + "2024-03-01 | \n", + "5.33 | \n", + "
| 3 | \n", + "2024-02-01 | \n", + "5.33 | \n", + "
| 4 | \n", + "2024-01-01 | \n", + "5.33 | \n", + "
| \n", + " | timestamp | \n", + "spy | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-01 | \n", + "546.3700 | \n", + "
| 1 | \n", + "2024-05-01 | \n", + "525.6718 | \n", + "
| 2 | \n", + "2024-04-01 | \n", + "500.3636 | \n", + "
| 3 | \n", + "2024-03-01 | \n", + "521.3857 | \n", + "
| 4 | \n", + "2024-02-01 | \n", + "504.8645 | \n", + "
| \n", + " | timestamp | \n", + "gld | \n", + "
|---|---|---|
| 0 | \n", + "2024-06-01 | \n", + "214.99 | \n", + "
| 1 | \n", + "2024-05-01 | \n", + "215.30 | \n", + "
| 2 | \n", + "2024-04-01 | \n", + "211.87 | \n", + "
| 3 | \n", + "2024-03-01 | \n", + "205.72 | \n", + "
| 4 | \n", + "2024-02-01 | \n", + "189.31 | \n", + "
| \n", + " | timestamp | \n", + "cpi | \n", + "fed | \n", + "spy | \n", + "gld | \n", + "
|---|---|---|---|---|---|
| timestamp | \n", + "\n", + " | \n", + " | \n", + " | \n", + " | \n", + " |
| 2005-04-01 | \n", + "2005-04-01 | \n", + "194.6 | \n", + "2.79 | \n", + "80.2135 | \n", + "43.35 | \n", + "
| 2005-03-01 | \n", + "2005-03-01 | \n", + "193.3 | \n", + "2.63 | \n", + "81.7450 | \n", + "42.82 | \n", + "
| 2005-02-01 | \n", + "2005-02-01 | \n", + "191.8 | \n", + "2.50 | \n", + "83.2672 | \n", + "43.52 | \n", + "
| 2005-01-01 | \n", + "2005-01-01 | \n", + "190.7 | \n", + "2.28 | \n", + "81.5622 | \n", + "42.22 | \n", + "
| 2004-12-01 | \n", + "2004-12-01 | \n", + "190.3 | \n", + "2.16 | \n", + "83.4328 | \n", + "43.80 | \n", + "